{"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/video-recognition/papers/ran/1","list_of":"/task/video-recognition","task":"Video 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":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,64],"of":64,"counts":{"archive_papers_tagged":307,"with_a_code_link":168,"where_syntology_ran_a_sample":64,"not_listed_spam_title":0,"listed":307,"listed_where_code_ran":64,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":56,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":56,"listed_every_run_a_failure_of_syntologys_instrument":8,"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/video-recognition/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/mote-reconciling-generalization-with","slug":"mote-reconciling-generalization-with","title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","date":"2024-10-14","arxiv_id":"2410.10589","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mote-reconciling-generalization-with#ran","syntology_url":"https://syntology.ai/paper/2410.10589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10589"}},"official":{"repos":["zmhh-h/mote"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/demamba-ai-generated-video-detection-on","slug":"demamba-ai-generated-video-detection-on","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","date":"2024-05-30","arxiv_id":"2405.19707","repositories_listed":1,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/demamba-ai-generated-video-detection-on#ran","syntology_url":"https://syntology.ai/paper/2405.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19707"}},"official":{"repos":["chenhaoxing/DeMamba"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-tuning-towards-parameter-and","slug":"dynamic-tuning-towards-parameter-and","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","date":"2024-03-18","arxiv_id":"2403.11808","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":6,"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/dynamic-tuning-towards-parameter-and#ran","syntology_url":"https://syntology.ai/paper/2403.11808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11808"}},"official":{"repos":["nus-hpc-ai-lab/dynamic-tuning"],"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/ost-refining-text-knowledge-with-optimal","slug":"ost-refining-text-knowledge-with-optimal","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","date":"2023-11-30","arxiv_id":"2312.00096","repositories_listed":1,"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":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) · 1 unverified","sample_list":"/paper/ost-refining-text-knowledge-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2312.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00096"}},"official":{"repos":["tomchen-ctj/OST"],"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/object-centric-video-representation-for-long","slug":"object-centric-video-representation-for-long","title":"Object-centric Video Representation for Long-term Action Anticipation","date":"2023-10-31","arxiv_id":"2311.00180","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 3 unverified","sample_list":"/paper/object-centric-video-representation-for-long#ran","syntology_url":"https://syntology.ai/paper/2311.00180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00180"}},"official":{"repos":["brown-palm/ObjectPrompt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained","slug":"zeroi2v-zero-cost-adaptation-of-pre-trained","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","date":"2023-10-02","arxiv_id":"2310.01324","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2310.01324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01324"}},"official":{"repos":["mcg-nju/zeroi2v","leexinhao/ZeroI2V"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/disentangling-spatial-and-temporal-learning","slug":"disentangling-spatial-and-temporal-learning","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","date":"2023-09-14","arxiv_id":"2309.07911","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":6,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":10,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/disentangling-spatial-and-temporal-learning#ran","syntology_url":"https://syntology.ai/paper/2309.07911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07911"}},"official":{"repos":["alibaba-mmai-research/dist"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/eventful-transformers-leveraging-temporal","slug":"eventful-transformers-leveraging-temporal","title":"Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers","date":"2023-08-25","arxiv_id":"2308.13494","repositories_listed":1,"syntology":{"n":25,"n_ran":7,"n_constructed":1,"n_ran_checked":3,"n_instrument":4,"n_unverified":18,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/eventful-transformers-leveraging-temporal#ran","syntology_url":"https://syntology.ai/paper/2308.13494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13494"}},"official":{"repos":["WISION-Lab/eventful-transformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":18,"ran_from_kinds":["official"]}}},{"url":"/paper/audio-visual-class-incremental-learning","slug":"audio-visual-class-incremental-learning","title":"Audio-Visual Class-Incremental Learning","date":"2023-08-21","arxiv_id":"2308.11073","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"7 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/audio-visual-class-incremental-learning#ran","syntology_url":"https://syntology.ai/paper/2308.11073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11073"}},"official":{"repos":["weiguopian/av-cil_iccv2023"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/helping-hands-an-object-aware-ego-centric","slug":"helping-hands-an-object-aware-ego-centric","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","date":"2023-08-15","arxiv_id":"2308.07918","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":2,"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/helping-hands-an-object-aware-ego-centric#ran","syntology_url":"https://syntology.ai/paper/2308.07918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07918"}},"official":{"repos":["chuhanxx/helping_hand_for_egocentric_videos"],"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/orthogonal-temporal-interpolation-for-zero","slug":"orthogonal-temporal-interpolation-for-zero","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","date":"2023-08-14","arxiv_id":"2308.06897","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/orthogonal-temporal-interpolation-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.06897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06897"}},"official":{"repos":["sweetorangezhuyan/mm2023_oti"],"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/prune-spatio-temporal-tokens-by-semantic","slug":"prune-spatio-temporal-tokens-by-semantic","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","date":"2023-08-08","arxiv_id":"2308.04549","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"14 ran (of which 0 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) · 3 unverified","sample_list":"/paper/prune-spatio-temporal-tokens-by-semantic#ran","syntology_url":"https://syntology.ai/paper/2308.04549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04549"}},"official":{"repos":["mark12ding/sta"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/what-can-simple-arithmetic-operations-do-for","slug":"what-can-simple-arithmetic-operations-do-for","title":"What Can Simple Arithmetic Operations Do for Temporal Modeling?","date":"2023-07-18","arxiv_id":"2307.08908","repositories_listed":2,"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/what-can-simple-arithmetic-operations-do-for#ran","syntology_url":"https://syntology.ai/paper/2307.08908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08908"}},"official":{"repos":["whwu95/ATM"],"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/video-focalnets-spatio-temporal-focal","slug":"video-focalnets-spatio-temporal-focal","title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition","date":"2023-07-13","arxiv_id":"2307.06947","repositories_listed":3,"syntology":{"n":32,"n_ran":23,"n_constructed":7,"n_ran_checked":22,"n_instrument":1,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":21,"n_pointer_only":21,"phrase":"23 ran (of which 7 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/video-focalnets-spatio-temporal-focal#ran","syntology_url":"https://syntology.ai/paper/2307.06947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06947"}},"official":{"repos":["talalwasim/video-focalnets"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hiera-a-hierarchical-vision-transformer","slug":"hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","arxiv_id":"2306.00989","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hiera-a-hierarchical-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}},"official":{"repos":["facebookresearch/hiera"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-temporal-modeling-with-learnable","slug":"implicit-temporal-modeling-with-learnable","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","date":"2023-04-20","arxiv_id":"2304.10465","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/implicit-temporal-modeling-with-learnable#ran","syntology_url":"https://syntology.ai/paper/2304.10465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10465"}},"official":{"repos":["francis-rings/ila"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/use-your-head-improving-long-tail-video","slug":"use-your-head-improving-long-tail-video","title":"Use Your Head: Improving Long-Tail Video Recognition","date":"2023-04-03","arxiv_id":"2304.01143","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/use-your-head-improving-long-tail-video#ran","syntology_url":"https://syntology.ai/paper/2304.01143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01143"}},"official":{"repos":["tobyperrett/lmr-release"],"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/frame-flexible-network","slug":"frame-flexible-network","title":"Frame Flexible Network","date":"2023-03-26","arxiv_id":"2303.14817","repositories_listed":2,"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":0,"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/frame-flexible-network#ran","syntology_url":"https://syntology.ai/paper/2303.14817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14817"}},"official":{"repos":["bespontaneous/ffn"],"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/making-vision-transformers-efficient-from-a","slug":"making-vision-transformers-efficient-from-a","title":"Making Vision Transformers Efficient from A Token Sparsification View","date":"2023-03-15","arxiv_id":"2303.08685","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/making-vision-transformers-efficient-from-a#ran","syntology_url":"https://syntology.ai/paper/2303.08685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08685"}},"official":{"repos":["changsn/STViT-R"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/match-expand-and-improve-unsupervised","slug":"match-expand-and-improve-unsupervised","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","date":"2023-03-15","arxiv_id":"2303.08914","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/match-expand-and-improve-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2303.08914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08914"}},"official":{"repos":["wlin-at/maxi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-movie-scene-detection-using-state","slug":"efficient-movie-scene-detection-using-state","title":"Efficient Movie Scene Detection using State-Space Transformers","date":"2022-12-29","arxiv_id":"2212.14427","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-movie-scene-detection-using-state#ran","syntology_url":"https://syntology.ai/paper/2212.14427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14427"}},"official":{"repos":["md-mohaiminul/trans4mer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/look-more-but-care-less-in-video-recognition","slug":"look-more-but-care-less-in-video-recognition","title":"Look More but Care Less in Video Recognition","date":"2022-11-18","arxiv_id":"2211.09992","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/look-more-but-care-less-in-video-recognition#ran","syntology_url":"https://syntology.ai/paper/2211.09992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09992"}},"official":{"repos":["bespontaneous/afnet-pytorch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cluster-and-aggregate-face-recognition-with","slug":"cluster-and-aggregate-face-recognition-with","title":"Cluster and Aggregate: Face Recognition with Large Probe Set","date":"2022-10-19","arxiv_id":"2210.10864","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":6,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"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; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cluster-and-aggregate-face-recognition-with#ran","syntology_url":"https://syntology.ai/paper/2210.10864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10864"}},"official":{"repos":["mk-minchul/caface"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-unified-view-on-visual-parameter","slug":"towards-a-unified-view-on-visual-parameter","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","date":"2022-10-03","arxiv_id":"2210.00788","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":8,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-a-unified-view-on-visual-parameter#ran","syntology_url":"https://syntology.ai/paper/2210.00788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00788"}},"official":{"repos":["bruceyo/V-PETL"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-resolution-in-the-context-of","slug":"rethinking-resolution-in-the-context-of","title":"Rethinking Resolution in the Context of Efficient Video Recognition","date":"2022-09-26","arxiv_id":"2209.12797","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/rethinking-resolution-in-the-context-of#ran","syntology_url":"https://syntology.ai/paper/2209.12797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12797"}},"official":{"repos":["cvmi-lab/reskd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-online-video-detection-with","slug":"real-time-online-video-detection-with","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","date":"2022-09-19","arxiv_id":"2209.09236","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/real-time-online-video-detection-with#ran","syntology_url":"https://syntology.ai/paper/2209.09236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09236"}},"official":{"repos":["zhaoyue-zephyrus/testra"],"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/frozen-clip-models-are-efficient-video","slug":"frozen-clip-models-are-efficient-video","title":"Frozen CLIP Models are Efficient Video Learners","date":"2022-08-06","arxiv_id":"2208.03550","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":3,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"5 ran (of which 3 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) · 5 unverified","sample_list":"/paper/frozen-clip-models-are-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2208.03550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03550"}},"official":{"repos":["opengvlab/efficient-video-recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"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/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/long-movie-clip-classification-with-state","slug":"long-movie-clip-classification-with-state","title":"Long Movie Clip Classification with State-Space Video Models","date":"2022-04-04","arxiv_id":"2204.01692","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":2,"n_ran_checked":3,"n_instrument":8,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/long-movie-clip-classification-with-state#ran","syntology_url":"https://syntology.ai/paper/2204.01692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01692"}},"official":{"repos":["md-mohaiminul/ViS4mer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official","unlocated"]}}},{"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/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/optimization-planning-for-3d-convnets-1","slug":"optimization-planning-for-3d-convnets-1","title":"Optimization Planning for 3D ConvNets","date":"2022-01-11","arxiv_id":"2201.04021","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/optimization-planning-for-3d-convnets-1#ran","syntology_url":"https://syntology.ai/paper/2201.04021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04021"}},"official":{"repos":["zhaofanqiu/optimization-planning-for-3d-convnets"],"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/glance-and-focus-networks-for-dynamic-visual","slug":"glance-and-focus-networks-for-dynamic-visual","title":"Glance and Focus Networks for Dynamic Visual Recognition","date":"2022-01-09","arxiv_id":"2201.03014","repositories_listed":1,"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":3,"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/glance-and-focus-networks-for-dynamic-visual#ran","syntology_url":"https://syntology.ai/paper/2201.03014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03014"}},"official":{"repos":["blackfeather-wang/GFNet-Pytorch"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-attentive-covariance-pooling","slug":"temporal-attentive-covariance-pooling","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","date":"2021-10-27","arxiv_id":"2110.14381","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/temporal-attentive-covariance-pooling#ran","syntology_url":"https://syntology.ai/paper/2110.14381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14381"}},"official":{"repos":["ZilinGao/Temporal-attentive-Covariance-Pooling-Networks-for-Video-Recognition"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/dynamic-network-quantization-for-efficient","slug":"dynamic-network-quantization-for-efficient","title":"Dynamic Network Quantization for Efficient Video Inference","date":"2021-08-23","arxiv_id":"2108.10394","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dynamic-network-quantization-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2108.10394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10394"}},"official":null}},{"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/tokenlearner-what-can-8-learned-tokens-do-for","slug":"tokenlearner-what-can-8-learned-tokens-do-for","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","date":"2021-06-21","arxiv_id":"2106.11297","repositories_listed":11,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 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/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}},"official":{"repos":["google-research/scenic"],"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/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/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/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/adamml-adaptive-multi-modal-learning-for","slug":"adamml-adaptive-multi-modal-learning-for","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","date":"2021-05-11","arxiv_id":"2105.05165","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/adamml-adaptive-multi-modal-learning-for#ran","syntology_url":"https://syntology.ai/paper/2105.05165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05165"}},"official":null}},{"url":"/paper/adaptive-focus-for-efficient-video","slug":"adaptive-focus-for-efficient-video","title":"Adaptive Focus for Efficient Video Recognition","date":"2021-05-07","arxiv_id":"2105.03245","repositories_listed":2,"syntology":{"n":23,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":23,"phrase":"13 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; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/adaptive-focus-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2105.03245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03245"}},"official":{"repos":["blackfeather-wang/AdaFocus"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/videolt-large-scale-long-tailed-video","slug":"videolt-large-scale-long-tailed-video","title":"VideoLT: Large-scale Long-tailed Video Recognition","date":"2021-05-06","arxiv_id":"2105.02668","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/videolt-large-scale-long-tailed-video#ran","syntology_url":"https://syntology.ai/paper/2105.02668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02668"}},"official":{"repos":["17Skye17/VideoLT"],"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/frameexit-conditional-early-exiting-for","slug":"frameexit-conditional-early-exiting-for","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","date":"2021-04-27","arxiv_id":"2104.13400","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":1,"n_ran_checked":2,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/frameexit-conditional-early-exiting-for#ran","syntology_url":"https://syntology.ai/paper/2104.13400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13400"}},"official":{"repos":["Qualcomm-AI-research/FrameExit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/visual-semantic-role-labeling-for-video","slug":"visual-semantic-role-labeling-for-video","title":"Visual Semantic Role Labeling for Video Understanding","date":"2021-04-02","arxiv_id":"2104.00990","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-semantic-role-labeling-for-video#ran","syntology_url":"https://syntology.ai/paper/2104.00990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00990"}},"official":{"repos":["TheShadow29/VidSitu"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-versatile-neural-architectures-by","slug":"learning-versatile-neural-architectures-by","title":"Learning Versatile Neural Architectures by Propagating Network Codes","date":"2021-03-24","arxiv_id":"2103.13253","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":4,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-versatile-neural-architectures-by#ran","syntology_url":"https://syntology.ai/paper/2103.13253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13253"}},"official":{"repos":["dingmyu/NCP"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":4,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/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-video-representation-learning-3","slug":"self-supervised-video-representation-learning-3","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","date":"2020-08-06","arxiv_id":"2008.02531","repositories_listed":2,"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/self-supervised-video-representation-learning-3#ran","syntology_url":"https://syntology.ai/paper/2008.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02531"}},"official":{"repos":["BestJuly/Inter-intra-video-contrastive-learning"],"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/adversarial-bipartite-graph-learning-for","slug":"adversarial-bipartite-graph-learning-for","title":"Adversarial Bipartite Graph Learning for Video Domain Adaptation","date":"2020-07-31","arxiv_id":"2007.15829","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/adversarial-bipartite-graph-learning-for#ran","syntology_url":"https://syntology.ai/paper/2007.15829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15829"}},"official":{"repos":["Luoyadan/MM2020_ABG"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tam-temporal-adaptive-module-for-video","slug":"tam-temporal-adaptive-module-for-video","title":"TAM: Temporal Adaptive Module for Video Recognition","date":"2020-05-14","arxiv_id":"2005.06803","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/tam-temporal-adaptive-module-for-video#ran","syntology_url":"https://syntology.ai/paper/2005.06803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.06803"}},"official":{"repos":["liu-zhy/TANet","liu-zhy/temporal-adaptive-module"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/would-mega-scale-datasets-further-enhance","slug":"would-mega-scale-datasets-further-enhance","title":"Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?","date":"2020-04-10","arxiv_id":"2004.04968","repositories_listed":10,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"16 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; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/would-mega-scale-datasets-further-enhance#ran","syntology_url":"https://syntology.ai/paper/2004.04968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04968"}},"official":{"repos":["kenshohara/3D-ResNets-PyTorch"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/improved-residual-networks-for-image-and","slug":"improved-residual-networks-for-image-and","title":"Improved Residual Networks for Image and Video Recognition","date":"2020-04-10","arxiv_id":"2004.04989","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 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/improved-residual-networks-for-image-and#ran","syntology_url":"https://syntology.ai/paper/2004.04989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04989"}},"official":{"repos":["iduta/iresnet"],"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"]}}},{"url":"/paper/x3d-expanding-architectures-for-efficient","slug":"x3d-expanding-architectures-for-efficient","title":"X3D: Expanding Architectures for Efficient Video Recognition","date":"2020-04-09","arxiv_id":"2004.04730","repositories_listed":8,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}},"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/omni-sourced-webly-supervised-learning-for","slug":"omni-sourced-webly-supervised-learning-for","title":"Omni-sourced Webly-supervised Learning for Video Recognition","date":"2020-03-29","arxiv_id":"2003.13042","repositories_listed":3,"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/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}},"official":{"repos":["open-mmlab/mmaction"],"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/clean-label-backdoor-attacks-on-video","slug":"clean-label-backdoor-attacks-on-video","title":"Clean-Label Backdoor Attacks on Video Recognition Models","date":"2020-03-06","arxiv_id":"2003.03030","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clean-label-backdoor-attacks-on-video#ran","syntology_url":"https://syntology.ai/paper/2003.03030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03030"}},"official":{"repos":["ShihaoZhaoZSH/Video-Backdoor-Attack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/drop-an-octave-reducing-spatial-redundancy-in","slug":"drop-an-octave-reducing-spatial-redundancy-in","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","date":"2019-04-10","arxiv_id":"1904.05049","repositories_listed":28,"syntology":{"n":34,"n_ran":24,"n_constructed":0,"n_ran_checked":11,"n_instrument":13,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":9,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/drop-an-octave-reducing-spatial-redundancy-in#ran","syntology_url":"https://syntology.ai/paper/1904.05049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05049"}},"official":{"repos":["facebookresearch/OctConv"],"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/slowfast-networks-for-video-recognition","slug":"slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","repositories_listed":15,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}},"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/temporal-shift-module-for-efficient-video","slug":"temporal-shift-module-for-efficient-video","title":"TSM: Temporal Shift Module for Efficient Video Understanding","date":"2018-11-20","arxiv_id":"1811.08383","repositories_listed":13,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"10 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; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-shift-module-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/1811.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08383"}},"official":{"repos":["MIT-HAN-LAB/temporal-shift-module"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/flow-guided-feature-aggregation-for-video","slug":"flow-guided-feature-aggregation-for-video","title":"Flow-Guided Feature Aggregation for Video Object Detection","date":"2017-03-29","arxiv_id":"1703.10025","repositories_listed":2,"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/flow-guided-feature-aggregation-for-video#ran","syntology_url":"https://syntology.ai/paper/1703.10025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10025"}},"official":{"repos":["msracver/Flow-Guided-Feature-Aggregation"],"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/deep-feature-flow-for-video-recognition","slug":"deep-feature-flow-for-video-recognition","title":"Deep Feature Flow for Video Recognition","date":"2016-11-23","arxiv_id":"1611.07715","repositories_listed":3,"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/deep-feature-flow-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1611.07715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.07715"}},"official":{"repos":["msracver/Deep-Feature-Flow"],"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"]}}}],"record_sha256":"0b27ef6924db71d72a10e977f13b06252866d81d6907ee20483437a3fa020715","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}