{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/action-recognition-in-videos/papers/ran/2","list_of":"/task/action-recognition-in-videos","task":"Action Recognition","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":275,"counts":{"archive_papers_tagged":2759,"with_a_code_link":1058,"where_syntology_ran_a_sample":275,"not_listed_spam_title":0,"listed":2759,"listed_where_code_ran":275,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":232,"every_run_a_failure_of_syntologys_instrument":43,"listed_with_a_run_with_no_instrument_failure":232,"listed_every_run_a_failure_of_syntologys_instrument":43,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/action-recognition-in-videos/papers/ran/1","prev":"/task/action-recognition-in-videos/papers/ran/1","next":"/task/action-recognition-in-videos/papers/ran/3","papers":[{"url":"/paper/hierarchical-temporal-transformer-for-3d-hand","slug":"hierarchical-temporal-transformer-for-3d-hand","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","date":"2022-09-20","arxiv_id":"2209.09484","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hierarchical-temporal-transformer-for-3d-hand#ran","syntology_url":"https://syntology.ai/paper/2209.09484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09484"}},"official":{"repos":["fylwen/htt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchically-decomposed-graph-convolutional","slug":"hierarchically-decomposed-graph-convolutional","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2022-08-23","arxiv_id":"2208.10741","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":7,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hierarchically-decomposed-graph-convolutional#ran","syntology_url":"https://syntology.ai/paper/2208.10741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10741"}},"official":{"repos":["Jho-Yonsei/HD-GCN"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-video-domain-adaptation-for-1","slug":"unsupervised-video-domain-adaptation-for-1","title":"Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective","date":"2022-08-15","arxiv_id":"2208.07365","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unsupervised-video-domain-adaptation-for-1#ran","syntology_url":"https://syntology.ai/paper/2208.07365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07365"}},"official":{"repos":["ldkong1205/transvae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/language-supervised-training-for-skeleton","slug":"language-supervised-training-for-skeleton","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","date":"2022-08-10","arxiv_id":"2208.05318","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-supervised-training-for-skeleton#ran","syntology_url":"https://syntology.ai/paper/2208.05318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05318"}},"official":{"repos":["martinxm/gap","martinxm/lst"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sports-video-analysis-on-large-scale-data","slug":"sports-video-analysis-on-large-scale-data","title":"Sports Video Analysis on Large-Scale Data","date":"2022-08-09","arxiv_id":"2208.04897","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sports-video-analysis-on-large-scale-data#ran","syntology_url":"https://syntology.ai/paper/2208.04897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.04897"}},"official":{"repos":["jackwu502/nsva"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/privacy-preserving-action-recognition-via","slug":"privacy-preserving-action-recognition-via","title":"Privacy-Preserving Action Recognition via Motion Difference Quantization","date":"2022-08-04","arxiv_id":"2208.02459","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/privacy-preserving-action-recognition-via#ran","syntology_url":"https://syntology.ai/paper/2208.02459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02459"}},"official":{"repos":["suakaw/bdq_privacyar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/expanding-language-image-pretrained-models","slug":"expanding-language-image-pretrained-models","title":"Expanding Language-Image Pretrained Models for General Video Recognition","date":"2022-08-04","arxiv_id":"2208.02816","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}},"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spatiotemporal-self-attention-modeling-with","slug":"spatiotemporal-self-attention-modeling-with","title":"Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition","date":"2022-07-27","arxiv_id":"2207.13259","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/spatiotemporal-self-attention-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2207.13259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13259"}},"official":{"repos":["martinxm/tps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchically-self-supervised-transformer","slug":"hierarchically-self-supervised-transformer","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","date":"2022-07-20","arxiv_id":"2207.09644","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":5,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hierarchically-self-supervised-transformer#ran","syntology_url":"https://syntology.ai/paper/2207.09644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09644"}},"official":{"repos":["yuxiaochen1103/Hi-TRS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/discover-and-mitigate-unknown-biases-with","slug":"discover-and-mitigate-unknown-biases-with","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","date":"2022-07-20","arxiv_id":"2207.10077","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/discover-and-mitigate-unknown-biases-with#ran","syntology_url":"https://syntology.ai/paper/2207.10077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10077"}},"official":{"repos":["zhihengli-UR/DebiAN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/time-is-matter-temporal-self-supervision-for","slug":"time-is-matter-temporal-self-supervision-for","title":"Time Is MattEr: Temporal Self-supervision for Video Transformers","date":"2022-07-19","arxiv_id":"2207.09067","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/time-is-matter-temporal-self-supervision-for#ran","syntology_url":"https://syntology.ai/paper/2207.09067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09067"}},"official":{"repos":["alinlab/temporal-selfsupervision"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-scale-spatial-temporal-graph","slug":"multi-scale-spatial-temporal-graph","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","date":"2022-06-27","arxiv_id":"2206.13028","repositories_listed":1,"syntology":{"n":26,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/multi-scale-spatial-temporal-graph#ran","syntology_url":"https://syntology.ai/paper/2206.13028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13028"}},"official":{"repos":["czhaneva/mst-gcn"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/parameter-efficient-image-to-video-transfer","slug":"parameter-efficient-image-to-video-transfer","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","date":"2022-06-27","arxiv_id":"2206.13559","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/parameter-efficient-image-to-video-transfer#ran","syntology_url":"https://syntology.ai/paper/2206.13559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13559"}},"official":{"repos":["linziyi96/st-adapter"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-viewpoint-agnostic-visual","slug":"learning-viewpoint-agnostic-visual","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","date":"2022-06-23","arxiv_id":"2206.11895","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-viewpoint-agnostic-visual#ran","syntology_url":"https://syntology.ai/paper/2206.11895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11895"}},"official":{"repos":["elicassion/3dtrl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/revealing-single-frame-bias-for-video-and","slug":"revealing-single-frame-bias-for-video-and","title":"Revealing Single Frame Bias for Video-and-Language Learning","date":"2022-06-07","arxiv_id":"2206.03428","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revealing-single-frame-bias-for-video-and#ran","syntology_url":"https://syntology.ai/paper/2206.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03428"}},"official":{"repos":["jayleicn/singularity"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-deeper-dive-into-what-deep-spatiotemporal-1","slug":"a-deeper-dive-into-what-deep-spatiotemporal-1","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","date":"2022-06-06","arxiv_id":"2206.02846","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-deeper-dive-into-what-deep-spatiotemporal-1#ran","syntology_url":"https://syntology.ai/paper/2206.02846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02846"}},"official":{"repos":["YorkUCVIL/Static-Dynamic-Interpretability"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/egocentric-video-language-pretraining","slug":"egocentric-video-language-pretraining","title":"Egocentric Video-Language Pretraining","date":"2022-06-03","arxiv_id":"2206.01670","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/egocentric-video-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2206.01670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01670"}},"official":{"repos":["showlab/egovlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cross-architecture-self-supervised-video","slug":"cross-architecture-self-supervised-video","title":"Cross-Architecture Self-supervised Video Representation Learning","date":"2022-05-26","arxiv_id":"2205.13313","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/cross-architecture-self-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2205.13313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13313"}},"official":{"repos":["guoshengcv/cacl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptformer-adapting-vision-transformers-for","slug":"adaptformer-adapting-vision-transformers-for","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","date":"2022-05-26","arxiv_id":"2205.13535","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptformer-adapting-vision-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2205.13535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13535"}},"official":{"repos":["ShoufaChen/AdaptFormer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-alignment-networks-for-long-term","slug":"temporal-alignment-networks-for-long-term","title":"Temporal Alignment Networks for Long-term Video","date":"2022-04-06","arxiv_id":"2204.02968","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-alignment-networks-for-long-term#ran","syntology_url":"https://syntology.ai/paper/2204.02968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02968"}},"official":null}},{"url":"/paper/occamnets-mitigating-dataset-bias-by-favoring","slug":"occamnets-mitigating-dataset-bias-by-favoring","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","date":"2022-04-05","arxiv_id":"2204.02426","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/occamnets-mitigating-dataset-bias-by-favoring#ran","syntology_url":"https://syntology.ai/paper/2204.02426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02426"}},"official":{"repos":["erobic/occam-nets-v1"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/tallformer-temporal-action-localization-with","slug":"tallformer-temporal-action-localization-with","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","date":"2022-04-04","arxiv_id":"2204.01680","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tallformer-temporal-action-localization-with#ran","syntology_url":"https://syntology.ai/paper/2204.01680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01680"}},"official":{"repos":["klauscc/tallformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spact-self-supervised-privacy-preservation","slug":"spact-self-supervised-privacy-preservation","title":"SPAct: Self-supervised Privacy Preservation for Action Recognition","date":"2022-03-29","arxiv_id":"2203.15205","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/spact-self-supervised-privacy-preservation#ran","syntology_url":"https://syntology.ai/paper/2203.15205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15205"}},"official":{"repos":["daveishan/spact"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/class-incremental-learning-for-action-1","slug":"class-incremental-learning-for-action-1","title":"Class-Incremental Learning for Action Recognition in Videos","date":"2022-03-25","arxiv_id":"2203.13611","repositories_listed":0,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/class-incremental-learning-for-action-1#ran","syntology_url":"https://syntology.ai/paper/2203.13611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13611"}},"official":null}},{"url":"/paper/fitclip-refining-large-scale-pretrained-image","slug":"fitclip-refining-large-scale-pretrained-image","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","date":"2022-03-24","arxiv_id":"2203.13371","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fitclip-refining-large-scale-pretrained-image#ran","syntology_url":"https://syntology.ai/paper/2203.13371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13371"}},"official":{"repos":["bryant1410/fitclip","bryant1410/tclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videomae-masked-autoencoders-are-data-1","slug":"videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","repositories_listed":9,"syntology":{"n":13,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}},"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/direcformer-a-directed-attention-in","slug":"direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","arxiv_id":"2203.10233","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/direcformer-a-directed-attention-in#ran","syntology_url":"https://syntology.ai/paper/2203.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10233"}},"official":{"repos":["uark-cviu/direcformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/group-contextualization-for-video-recognition","slug":"group-contextualization-for-video-recognition","title":"Group Contextualization for Video Recognition","date":"2022-03-18","arxiv_id":"2203.09694","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/group-contextualization-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/2203.09694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09694"}},"official":{"repos":["haoyanbin918/group-contextualization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-temporal-consistency-for-source-free","slug":"learning-temporal-consistency-for-source-free","title":"Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition","date":"2022-03-09","arxiv_id":"2203.04559","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-temporal-consistency-for-source-free#ran","syntology_url":"https://syntology.ai/paper/2203.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04559"}},"official":{"repos":["xuyu0010/atcon"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/source-free-progressive-graph-learning-for","slug":"source-free-progressive-graph-learning-for","title":"Source-Free Progressive Graph Learning for Open-Set Domain Adaptation","date":"2022-02-13","arxiv_id":"2202.06174","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/source-free-progressive-graph-learning-for#ran","syntology_url":"https://syntology.ai/paper/2202.06174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06174"}},"official":{"repos":["BUserName/PGL","luoyadan/sf-pgl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/capturing-temporal-information-in-a-single","slug":"capturing-temporal-information-in-a-single","title":"Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition","date":"2022-01-25","arxiv_id":"2201.10394","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/capturing-temporal-information-in-a-single#ran","syntology_url":"https://syntology.ai/paper/2201.10394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10394"}},"official":{"repos":["kiyoon/channel_sampling"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/omnivore-a-single-model-for-many-visual","slug":"omnivore-a-single-model-for-many-visual","title":"Omnivore: A Single Model for Many Visual Modalities","date":"2022-01-20","arxiv_id":"2201.08377","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}},"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bridgeformer-bridging-video-text-retrieval","slug":"bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","repositories_listed":2,"syntology":{"n":24,"n_ran":13,"n_constructed":8,"n_ran_checked":9,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":6,"phrase":"13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/bridgeformer-bridging-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2201.04850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04850"}},"official":{"repos":["tencentarc/mcq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/spatio-temporal-tuples-transformer-for","slug":"spatio-temporal-tuples-transformer-for","title":"Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition","date":"2022-01-08","arxiv_id":"2201.02849","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/spatio-temporal-tuples-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2201.02849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.02849"}},"official":{"repos":["heleiqiu/sttformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/prompting-visual-language-models-for","slug":"prompting-visual-language-models-for","title":"Prompting Visual-Language Models for Efficient Video Understanding","date":"2021-12-08","arxiv_id":"2112.04478","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prompting-visual-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2112.04478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.04478"}},"official":{"repos":["ju-chen/Efficient-Prompt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/morphmlp-a-self-attention-free-mlp-like","slug":"morphmlp-a-self-attention-free-mlp-like","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","date":"2021-11-24","arxiv_id":"2111.12527","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/morphmlp-a-self-attention-free-mlp-like#ran","syntology_url":"https://syntology.ai/paper/2111.12527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12527"}},"official":{"repos":["MTLab/MorphMLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ubnormal-new-benchmark-for-supervised-open","slug":"ubnormal-new-benchmark-for-supervised-open","title":"UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection","date":"2021-11-16","arxiv_id":"2111.08644","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ubnormal-new-benchmark-for-supervised-open#ran","syntology_url":"https://syntology.ai/paper/2111.08644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08644"}},"official":{"repos":["lilygeorgescu/ubnormal"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-to-sequence-modeling-for-action-1","slug":"sequence-to-sequence-modeling-for-action-1","title":"Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution","date":"2021-11-03","arxiv_id":"2111.02521","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sequence-to-sequence-modeling-for-action-1#ran","syntology_url":"https://syntology.ai/paper/2111.02521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02521"}},"official":null}},{"url":"/paper/relational-self-attention-what-s-missing-in","slug":"relational-self-attention-what-s-missing-in","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","date":"2021-11-02","arxiv_id":"2111.01673","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/relational-self-attention-what-s-missing-in#ran","syntology_url":"https://syntology.ai/paper/2111.01673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01673"}},"official":{"repos":["KimManjin/RSA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/object-region-video-transformers-1","slug":"object-region-video-transformers-1","title":"Object-Region Video Transformers","date":"2021-10-13","arxiv_id":"2110.06915","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/object-region-video-transformers-1#ran","syntology_url":"https://syntology.ai/paper/2110.06915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06915"}},"official":null}},{"url":"/paper/unsupervised-motion-representation-learning","slug":"unsupervised-motion-representation-learning","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","date":"2021-10-01","arxiv_id":"2110.00529","repositories_listed":1,"syntology":{"n":20,"n_ran":15,"n_constructed":4,"n_ran_checked":8,"n_instrument":7,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":5,"n_pointer_only":0,"phrase":"15 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/unsupervised-motion-representation-learning#ran","syntology_url":"https://syntology.ai/paper/2110.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00529"}},"official":{"repos":["ZiweiXU/CapsuleMotion"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":4,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/actionclip-a-new-paradigm-for-video-action","slug":"actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/actionclip-a-new-paradigm-for-video-action#ran","syntology_url":"https://syntology.ai/paper/2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}},"official":{"repos":["sallymmx/actionclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/conditional-extreme-value-theory-for-open-set","slug":"conditional-extreme-value-theory-for-open-set","title":"Conditional Extreme Value Theory for Open Set Video Domain Adaptation","date":"2021-09-01","arxiv_id":"2109.00522","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/conditional-extreme-value-theory-for-open-set#ran","syntology_url":"https://syntology.ai/paper/2109.00522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00522"}},"official":{"repos":["zhuoxiao-chen/cevt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-multi-granular-spatio-temporal-graph","slug":"learning-multi-granular-spatio-temporal-graph","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","date":"2021-08-10","arxiv_id":"2108.04536","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-multi-granular-spatio-temporal-graph#ran","syntology_url":"https://syntology.ai/paper/2108.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04536"}},"official":{"repos":["tailin1009/dualhead-network"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skeleton-contrastive-3d-action-representation","slug":"skeleton-contrastive-3d-action-representation","title":"Skeleton-Contrastive 3D Action Representation Learning","date":"2021-08-08","arxiv_id":"2108.03656","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/skeleton-contrastive-3d-action-representation#ran","syntology_url":"https://syntology.ai/paper/2108.03656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03656"}},"official":{"repos":["fmthoker/skeleton-contrast"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/unifying-nonlocal-blocks-for-neural-networks","slug":"unifying-nonlocal-blocks-for-neural-networks","title":"Unifying Nonlocal Blocks for Neural Networks","date":"2021-08-05","arxiv_id":"2108.02451","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-nonlocal-blocks-for-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2108.02451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02451"}},"official":{"repos":["zh460045050/SNL_ICCV2021"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/elaborative-rehearsal-for-zero-shot-action","slug":"elaborative-rehearsal-for-zero-shot-action","title":"Elaborative Rehearsal for Zero-shot Action Recognition","date":"2021-08-05","arxiv_id":"2108.02833","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/elaborative-rehearsal-for-zero-shot-action#ran","syntology_url":"https://syntology.ai/paper/2108.02833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02833"}},"official":{"repos":["DeLightCMU/ElaborativeRehearsal"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/channel-wise-topology-refinement-graph","slug":"channel-wise-topology-refinement-graph","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","date":"2021-07-26","arxiv_id":"2107.12213","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/channel-wise-topology-refinement-graph#ran","syntology_url":"https://syntology.ai/paper/2107.12213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12213"}},"official":{"repos":["Uason-Chen/CTR-GCN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/evidential-deep-learning-for-open-set-action","slug":"evidential-deep-learning-for-open-set-action","title":"Evidential Deep Learning for Open Set Action Recognition","date":"2021-07-21","arxiv_id":"2107.10161","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evidential-deep-learning-for-open-set-action#ran","syntology_url":"https://syntology.ai/paper/2107.10161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.10161"}},"official":{"repos":["Cogito2012/DEAR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-image-classifier-can-suffice-video","slug":"an-image-classifier-can-suffice-video","title":"Can An Image Classifier Suffice For Action Recognition?","date":"2021-06-26","arxiv_id":"2106.14104","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-image-classifier-can-suffice-video#ran","syntology_url":"https://syntology.ai/paper/2106.14104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14104"}},"official":{"repos":["ibm/sifar-pytorch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","repositories_listed":15,"syntology":{"n":32,"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}},"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vimpac-video-pre-training-via-masked-token","slug":"vimpac-video-pre-training-via-masked-token","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","date":"2021-06-21","arxiv_id":"2106.11250","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vimpac-video-pre-training-via-masked-token#ran","syntology_url":"https://syntology.ai/paper/2106.11250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11250"}},"official":{"repos":["airsplay/vimpac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-long-form-video-understanding-1","slug":"towards-long-form-video-understanding-1","title":"Towards Long-Form Video Understanding","date":"2021-06-21","arxiv_id":"2106.11310","repositories_listed":2,"syntology":{"n":19,"n_ran":18,"n_constructed":0,"n_ran_checked":16,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":14,"n_pointer_only":2,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-long-form-video-understanding-1#ran","syntology_url":"https://syntology.ai/paper/2106.11310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11310"}},"official":{"repos":["chaoyuaw/lvu"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/modist-motion-distillation-for-self","slug":"modist-motion-distillation-for-self","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","date":"2021-06-17","arxiv_id":"2106.09703","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/modist-motion-distillation-for-self#ran","syntology_url":"https://syntology.ai/paper/2106.09703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09703"}},"official":{"repos":["amazon-science/self-supervised-maclr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/space-time-mixing-attention-for-video","slug":"space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","arxiv_id":"2106.05968","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/space-time-mixing-attention-for-video#ran","syntology_url":"https://syntology.ai/paper/2106.05968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05968"}},"official":{"repos":["1adrianb/video-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/keeping-your-eye-on-the-ball-trajectory","slug":"keeping-your-eye-on-the-ball-trajectory","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","date":"2021-06-09","arxiv_id":"2106.05392","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/keeping-your-eye-on-the-ball-trajectory#ran","syntology_url":"https://syntology.ai/paper/2106.05392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05392"}},"official":{"repos":["facebookresearch/Motionformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/regionvit-regional-to-local-attention-for","slug":"regionvit-regional-to-local-attention-for","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","date":"2021-06-04","arxiv_id":"2106.02689","repositories_listed":4,"syntology":{"n":25,"n_ran":13,"n_constructed":9,"n_ran_checked":11,"n_instrument":2,"n_unverified":12,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"13 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/regionvit-regional-to-local-attention-for#ran","syntology_url":"https://syntology.ai/paper/2106.02689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02689"}},"official":{"repos":["IBM/RegionViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ct-net-channel-tensorization-network-for-1","slug":"ct-net-channel-tensorization-network-for-1","title":"CT-Net: Channel Tensorization Network for Video Classification","date":"2021-06-03","arxiv_id":"2106.01603","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":2,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ct-net-channel-tensorization-network-for-1#ran","syntology_url":"https://syntology.ai/paper/2106.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01603"}},"official":{"repos":["Andy1621/CT-Net"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-power-of-log-sum-exp-sequential-density","slug":"the-power-of-log-sum-exp-sequential-density","title":"The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization","date":"2021-05-28","arxiv_id":"2105.13636","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/the-power-of-log-sum-exp-sequential-density#ran","syntology_url":"https://syntology.ai/paper/2105.13636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13636"}},"official":{"repos":["TaikiMiyagawa/MSPRT-TANDEM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dsanet-dynamic-segment-aggregation-network","slug":"dsanet-dynamic-segment-aggregation-network","title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","date":"2021-05-25","arxiv_id":"2105.12085","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dsanet-dynamic-segment-aggregation-network#ran","syntology_url":"https://syntology.ai/paper/2105.12085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12085"}},"official":{"repos":["whwu95/DSANet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vpn-rethinking-video-pose-embeddings-for","slug":"vpn-rethinking-video-pose-embeddings-for","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","date":"2021-05-17","arxiv_id":"2105.08141","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vpn-rethinking-video-pose-embeddings-for#ran","syntology_url":"https://syntology.ai/paper/2105.08141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08141"}},"official":{"repos":["srijandas07/vpnplusplus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mutualnet-adaptive-convnet-via-mutual","slug":"mutualnet-adaptive-convnet-via-mutual","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","date":"2021-05-14","arxiv_id":"2105.07085","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mutualnet-adaptive-convnet-via-mutual#ran","syntology_url":"https://syntology.ai/paper/2105.07085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.07085"}},"official":{"repos":["taoyang1122/MutualNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/home-action-genome-cooperative-compositional","slug":"home-action-genome-cooperative-compositional","title":"Home Action Genome: Cooperative Compositional Action Understanding","date":"2021-05-11","arxiv_id":"2105.05226","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/home-action-genome-cooperative-compositional#ran","syntology_url":"https://syntology.ai/paper/2105.05226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05226"}},"official":{"repos":["nishantrai18/homage"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/3d-human-action-representation-learning-via","slug":"3d-human-action-representation-learning-via","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","date":"2021-04-29","arxiv_id":"2104.14466","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3d-human-action-representation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2104.14466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14466"}},"official":{"repos":["LinguoLi/CrosSCLR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/imagenet-21k-pretraining-for-the-masses","slug":"imagenet-21k-pretraining-for-the-masses","title":"ImageNet-21K Pretraining for the Masses","date":"2021-04-22","arxiv_id":"2104.10972","repositories_listed":5,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imagenet-21k-pretraining-for-the-masses#ran","syntology_url":"https://syntology.ai/paper/2104.10972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10972"}},"official":{"repos":["Alibaba-MIIL/ImageNet21K"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multiscale-vision-transformers","slug":"multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","repositories_listed":8,"syntology":{"n":26,"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":5,"phrase":"13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}},"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mgsampler-an-explainable-sampling-strategy","slug":"mgsampler-an-explainable-sampling-strategy","title":"MGSampler: An Explainable Sampling Strategy for Video Action Recognition","date":"2021-04-20","arxiv_id":"2104.09952","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mgsampler-an-explainable-sampling-strategy#ran","syntology_url":"https://syntology.ai/paper/2104.09952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09952"}},"official":{"repos":["mcg-nju/mgsampler"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/action-conditioned-3d-human-motion-synthesis","slug":"action-conditioned-3d-human-motion-synthesis","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","date":"2021-04-12","arxiv_id":"2104.05670","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/action-conditioned-3d-human-motion-synthesis#ran","syntology_url":"https://syntology.ai/paper/2104.05670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05670"}},"official":{"repos":["Mathux/ACTOR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/uav-human-a-large-benchmark-for-human","slug":"uav-human-a-large-benchmark-for-human","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","date":"2021-04-02","arxiv_id":"2104.00946","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uav-human-a-large-benchmark-for-human#ran","syntology_url":"https://syntology.ai/paper/2104.00946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00946"}},"official":{"repos":["SUTDCV/UAV-Human"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/2103-15691","slug":"2103-15691","title":"ViViT: A Video Vision Transformer","date":"2021-03-29","arxiv_id":"2103.15691","repositories_listed":10,"syntology":{"n":21,"n_ran":14,"n_constructed":10,"n_ran_checked":13,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}},"official":{"repos":["google-research/scenic"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/movinets-mobile-video-networks-for-efficient","slug":"movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","arxiv_id":"2103.11511","repositories_listed":3,"syntology":{"n":13,"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}},"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/action-net-multipath-excitation-for-action","slug":"action-net-multipath-excitation-for-action","title":"ACTION-Net: Multipath Excitation for Action Recognition","date":"2021-03-11","arxiv_id":"2103.07372","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/action-net-multipath-excitation-for-action#ran","syntology_url":"https://syntology.ai/paper/2103.07372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07372"}},"official":{"repos":["V-Sense/ACTION-Net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videomoco-contrastive-video-representation","slug":"videomoco-contrastive-video-representation","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","date":"2021-03-10","arxiv_id":"2103.05905","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/videomoco-contrastive-video-representation#ran","syntology_url":"https://syntology.ai/paper/2103.05905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05905"}},"official":{"repos":["tinapan-pt/VideoMoCo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-the-robustness-of-skeleton","slug":"understanding-the-robustness-of-skeleton","title":"Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack","date":"2021-03-09","arxiv_id":"2103.05347","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/understanding-the-robustness-of-skeleton#ran","syntology_url":"https://syntology.ai/paper/2103.05347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05347"}},"official":{"repos":["realcrane/SMART"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":2,"n_instrument":14,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":16,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}},"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/learning-self-similarity-in-space-and-time-as-1","slug":"learning-self-similarity-in-space-and-time-as-1","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","date":"2021-02-14","arxiv_id":"2102.07092","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-self-similarity-in-space-and-time-as-1#ran","syntology_url":"https://syntology.ai/paper/2102.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07092"}},"official":{"repos":["arunos728/SELFY"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/is-space-time-attention-all-you-need-for","slug":"is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","arxiv_id":"2102.05095","repositories_listed":16,"syntology":{"n":43,"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":14,"phrase":"35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}},"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/negative-data-augmentation-1","slug":"negative-data-augmentation-1","title":"Negative Data Augmentation","date":"2021-02-09","arxiv_id":"2102.05113","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/negative-data-augmentation-1#ran","syntology_url":"https://syntology.ai/paper/2102.05113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05113"}},"official":{"repos":["ermongroup/NDA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/semi-supervised-action-recognition-with","slug":"semi-supervised-action-recognition-with","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","date":"2021-02-04","arxiv_id":"2102.02751","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semi-supervised-action-recognition-with#ran","syntology_url":"https://syntology.ai/paper/2102.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02751"}},"official":{"repos":["CVIR/TCL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/artemis-affective-language-for-visual-art","slug":"artemis-affective-language-for-visual-art","title":"ArtEmis: Affective Language for Visual Art","date":"2021-01-19","arxiv_id":"2101.07396","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/artemis-affective-language-for-visual-art#ran","syntology_url":"https://syntology.ai/paper/2101.07396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.07396"}},"official":{"repos":["optas/artemis"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/temporal-relational-crosstransformers-for-few","slug":"temporal-relational-crosstransformers-for-few","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","date":"2021-01-15","arxiv_id":"2101.06184","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/temporal-relational-crosstransformers-for-few#ran","syntology_url":"https://syntology.ai/paper/2101.06184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06184"}},"official":{"repos":["tobyperrett/trx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/tdn-temporal-difference-networks-for","slug":"tdn-temporal-difference-networks-for","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","date":"2020-12-18","arxiv_id":"2012.10071","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tdn-temporal-difference-networks-for#ran","syntology_url":"https://syntology.ai/paper/2012.10071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.10071"}},"official":{"repos":["MCG-NJU/TDN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/videomix-rethinking-data-augmentation-for","slug":"videomix-rethinking-data-augmentation-for","title":"VideoMix: Rethinking Data Augmentation for Video Classification","date":"2020-12-07","arxiv_id":"2012.03457","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videomix-rethinking-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2012.03457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.03457"}},"official":null}},{"url":"/paper/spatio-temporal-inception-graph-convolutional","slug":"spatio-temporal-inception-graph-convolutional","title":"Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2020-11-26","arxiv_id":"2011.13322","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatio-temporal-inception-graph-convolutional#ran","syntology_url":"https://syntology.ai/paper/2011.13322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.13322"}},"official":{"repos":["yellowtownhz/STIGCN"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/deep-analysis-of-cnn-based-spatio-temporal","slug":"deep-analysis-of-cnn-based-spatio-temporal","title":"Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition","date":"2020-10-22","arxiv_id":"2010.11757","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-analysis-of-cnn-based-spatio-temporal#ran","syntology_url":"https://syntology.ai/paper/2010.11757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11757"}},"official":{"repos":["IBM/action-recognition-pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/depth-guided-adaptive-meta-fusion-network-for","slug":"depth-guided-adaptive-meta-fusion-network-for","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","date":"2020-10-20","arxiv_id":"2010.09982","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/depth-guided-adaptive-meta-fusion-network-for#ran","syntology_url":"https://syntology.ai/paper/2010.09982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09982"}},"official":{"repos":["lovelyqian/AMeFu-Net"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-co-training-for-video","slug":"self-supervised-co-training-for-video","title":"Self-supervised Co-training for Video Representation Learning","date":"2020-10-19","arxiv_id":"2010.09709","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-co-training-for-video#ran","syntology_url":"https://syntology.ai/paper/2010.09709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09709"}},"official":{"repos":["TengdaHan/CoCLR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/what-can-you-learn-from-your-muscles-learning","slug":"what-can-you-learn-from-your-muscles-learning","title":"What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions","date":"2020-10-16","arxiv_id":"2010.08539","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/what-can-you-learn-from-your-muscles-learning#ran","syntology_url":"https://syntology.ai/paper/2010.08539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08539"}},"official":{"repos":["ehsanik/muscleTorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lifelong-graph-learning","slug":"lifelong-graph-learning","title":"Lifelong Graph Learning","date":"2020-09-01","arxiv_id":"2009.00647","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lifelong-graph-learning#ran","syntology_url":"https://syntology.ai/paper/2009.00647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.00647"}},"official":{"repos":["wang-chen/LGL","wang-chen/lgl-action-recognition"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-video-representation-learning-5","slug":"self-supervised-video-representation-learning-5","title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","date":"2020-08-31","arxiv_id":"2008.13426","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-video-representation-learning-5#ran","syntology_url":"https://syntology.ai/paper/2008.13426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.13426"}},"official":{"repos":["laura-wang/video_repres_sts"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/location-aware-graph-convolutional-networks","slug":"location-aware-graph-convolutional-networks","title":"Location-aware Graph Convolutional Networks for Video Question Answering","date":"2020-08-07","arxiv_id":"2008.09105","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/location-aware-graph-convolutional-networks#ran","syntology_url":"https://syntology.ai/paper/2008.09105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.09105"}},"official":{"repos":["SunDoge/L-GCN"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/seco-exploring-sequence-supervision-for","slug":"seco-exploring-sequence-supervision-for","title":"SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning","date":"2020-08-03","arxiv_id":"2008.00975","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seco-exploring-sequence-supervision-for#ran","syntology_url":"https://syntology.ai/paper/2008.00975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00975"}},"official":{"repos":["YihengZhang-CV/SeCo-Sequence-Contrastive-Learning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rareact-a-video-dataset-of-unusual","slug":"rareact-a-video-dataset-of-unusual","title":"RareAct: A video dataset of unusual interactions","date":"2020-08-03","arxiv_id":"2008.01018","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rareact-a-video-dataset-of-unusual#ran","syntology_url":"https://syntology.ai/paper/2008.01018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01018"}},"official":{"repos":["antoine77340/RareAct"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-augmented-dense-predictive-coding-for","slug":"memory-augmented-dense-predictive-coding-for","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","date":"2020-08-03","arxiv_id":"2008.01065","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/memory-augmented-dense-predictive-coding-for#ran","syntology_url":"https://syntology.ai/paper/2008.01065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01065"}},"official":{"repos":["TengdaHan/MemDPC"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/augmented-skeleton-based-contrastive-action","slug":"augmented-skeleton-based-contrastive-action","title":"Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition","date":"2020-08-01","arxiv_id":"2008.00188","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/augmented-skeleton-based-contrastive-action#ran","syntology_url":"https://syntology.ai/paper/2008.00188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00188"}},"official":{"repos":["Mikexu007/AS-CAL","Mikexu007/AS_CAL"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lemma-a-multi-view-dataset-for-learning-multi","slug":"lemma-a-multi-view-dataset-for-learning-multi","title":"LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities","date":"2020-07-31","arxiv_id":"2007.15781","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lemma-a-multi-view-dataset-for-learning-multi#ran","syntology_url":"https://syntology.ai/paper/2007.15781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15781"}},"official":{"repos":["Buzz-Beater/LEMMA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/motionsqueeze-neural-motion-feature-learning","slug":"motionsqueeze-neural-motion-feature-learning","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","date":"2020-07-20","arxiv_id":"2007.09933","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/motionsqueeze-neural-motion-feature-learning#ran","syntology_url":"https://syntology.ai/paper/2007.09933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09933"}},"official":null}},{"url":"/paper/learning-from-failure-training-debiased","slug":"learning-from-failure-training-debiased","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","date":"2020-07-06","arxiv_id":"2007.02561","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-from-failure-training-debiased#ran","syntology_url":"https://syntology.ai/paper/2007.02561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02561"}},"official":{"repos":["alinlab/BAR"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unsupervised-learning-of-video-1","slug":"unsupervised-learning-of-video-1","title":"Unsupervised Learning of Video Representations via Dense Trajectory Clustering","date":"2020-06-28","arxiv_id":"2006.15731","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-learning-of-video-1#ran","syntology_url":"https://syntology.ai/paper/2006.15731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15731"}},"official":{"repos":["pvtokmakov/video_cluster"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"2acf056601178ccc50c4ca311c97cd30c3a83f268ffcb912c7429650372ab299","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}