{"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/1","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":1,"pages_in_order":3,"rows_per_page":100,"rows":[1,100],"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":null,"next":"/task/action-recognition-in-videos/papers/ran/2","papers":[{"url":"/paper/hopadiff-holistic-partial-aware-fourier","slug":"hopadiff-holistic-partial-aware-fourier","title":"HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios","date":"2025-06-11","arxiv_id":"2506.09650","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":2,"n_no_contract":6,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hopadiff-holistic-partial-aware-fourier#ran","syntology_url":"https://syntology.ai/paper/2506.09650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09650"}},"official":{"repos":["kpeng9510/hopadiff"],"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/phi-bridging-domain-shift-in-long-term-action","slug":"phi-bridging-domain-shift-in-long-term-action","title":"PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction","date":"2025-05-26","arxiv_id":"2505.19972","repositories_listed":1,"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/phi-bridging-domain-shift-in-long-term-action#ran","syntology_url":"https://syntology.ai/paper/2505.19972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19972"}},"official":{"repos":["zhoukanglei/phi_aqa"],"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/temporal-alignment-free-video-matching-for-1","slug":"temporal-alignment-free-video-matching-for-1","title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","date":"2025-04-08","arxiv_id":"2504.05956","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"4 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/temporal-alignment-free-video-matching-for-1#ran","syntology_url":"https://syntology.ai/paper/2504.05956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05956"}},"official":{"repos":["leesb7426/team"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-generalize-without-bias-for-open","slug":"learning-to-generalize-without-bias-for-open","title":"Learning to Generalize without Bias for Open-Vocabulary Action Recognition","date":"2025-02-27","arxiv_id":"2502.20158","repositories_listed":0,"syntology":{"n":7,"n_ran":4,"n_constructed":4,"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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-to-generalize-without-bias-for-open#ran","syntology_url":"https://syntology.ai/paper/2502.20158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20158"}},"official":null}},{"url":"/paper/kronecker-mask-and-interpretive-prompts-are","slug":"kronecker-mask-and-interpretive-prompts-are","title":"Kronecker Mask and Interpretive Prompts are Language-Action Video Learners","date":"2025-02-05","arxiv_id":"2502.03549","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":9,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"9 ran (of which 9 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) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result","sample_list":"/paper/kronecker-mask-and-interpretive-prompts-are#ran","syntology_url":"https://syntology.ai/paper/2502.03549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03549"}},"official":{"repos":["yjyddq/CLAVER"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":9,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/frequency-aware-event-cloud-network","slug":"frequency-aware-event-cloud-network","title":"Frequency-aware Event Cloud Network","date":"2024-12-30","arxiv_id":"2412.20803","repositories_listed":0,"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":7,"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/frequency-aware-event-cloud-network#ran","syntology_url":"https://syntology.ai/paper/2412.20803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20803"}},"official":null}},{"url":"/paper/a-large-scale-study-on-video-action-dataset","slug":"a-large-scale-study-on-video-action-dataset","title":"A Large-Scale Study on Video Action Dataset Condensation","date":"2024-12-30","arxiv_id":"2412.21197","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":3,"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) · 4 unverified","sample_list":"/paper/a-large-scale-study-on-video-action-dataset#ran","syntology_url":"https://syntology.ai/paper/2412.21197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.21197"}},"official":{"repos":["mcg-nju/video-dc"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/chase-learning-convex-hull-adaptive-shift-for","slug":"chase-learning-convex-hull-adaptive-shift-for","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","date":"2024-10-09","arxiv_id":"2410.07153","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":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) · 0 unverified","sample_list":"/paper/chase-learning-convex-hull-adaptive-shift-for#ran","syntology_url":"https://syntology.ai/paper/2410.07153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07153"}},"official":{"repos":["Necolizer/CHASE"],"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":["official"]}}},{"url":"/paper/tasar-transferable-attack-on-skeletal-action","slug":"tasar-transferable-attack-on-skeletal-action","title":"TASAR: Transfer-based Attack on Skeletal Action Recognition","date":"2024-09-04","arxiv_id":"2409.02483","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/tasar-transferable-attack-on-skeletal-action#ran","syntology_url":"https://syntology.ai/paper/2409.02483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02483"}},"official":{"repos":["yunfengdiao/Skeleton-Robustness-Benchmark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modality-co-learning-for-efficient-1","slug":"multi-modality-co-learning-for-efficient-1","title":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","date":"2024-07-22","arxiv_id":"2407.15706","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-modality-co-learning-for-efficient-1#ran","syntology_url":"https://syntology.ai/paper/2407.15706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15706"}},"official":{"repos":["liujf69/MMCL-Action"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/c2c-component-to-composition-learning-for","slug":"c2c-component-to-composition-learning-for","title":"C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition","date":"2024-07-08","arxiv_id":"2407.06113","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/c2c-component-to-composition-learning-for#ran","syntology_url":"https://syntology.ai/paper/2407.06113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06113"}},"official":{"repos":["rongchangli/zscar_c2c"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dailydvs-200-a-comprehensive-benchmark","slug":"dailydvs-200-a-comprehensive-benchmark","title":"DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition","date":"2024-07-06","arxiv_id":"2407.05106","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"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) · 6 unverified","sample_list":"/paper/dailydvs-200-a-comprehensive-benchmark#ran","syntology_url":"https://syntology.ai/paper/2407.05106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05106"}},"official":{"repos":["qiwang233/dailydvs-200"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/awt-transferring-vision-language-models-via","slug":"awt-transferring-vision-language-models-via","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","date":"2024-07-05","arxiv_id":"2407.04603","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":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/awt-transferring-vision-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2407.04603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04603"}},"official":{"repos":["MCG-NJU/AWT"],"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/motion-meets-attention-video-motion-prompts","slug":"motion-meets-attention-video-motion-prompts","title":"Motion meets Attention: Video Motion Prompts","date":"2024-07-03","arxiv_id":"2407.03179","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"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) · 2 unverified","sample_list":"/paper/motion-meets-attention-video-motion-prompts#ran","syntology_url":"https://syntology.ai/paper/2407.03179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03179"}},"official":{"repos":["q1xiangchen/vmps"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/egovideo-exploring-egocentric-foundation","slug":"egovideo-exploring-egocentric-foundation","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","date":"2024-06-26","arxiv_id":"2406.18070","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/egovideo-exploring-egocentric-foundation#ran","syntology_url":"https://syntology.ai/paper/2406.18070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18070"}},"official":{"repos":["opengvlab/egovideo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/part-aware-unified-representation-of-language-1","slug":"part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","arxiv_id":"2406.13327","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":1,"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: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/part-aware-unified-representation-of-language-1#ran","syntology_url":"https://syntology.ai/paper/2406.13327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13327"}},"official":{"repos":["azzh1/purls"],"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/egonce-do-egocentric-video-language-models","slug":"egonce-do-egocentric-video-language-models","title":"EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?","date":"2024-05-28","arxiv_id":"2405.17719","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/egonce-do-egocentric-video-language-models#ran","syntology_url":"https://syntology.ai/paper/2405.17719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17719"}},"official":{"repos":["xuboshen/egoncepp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-efficient-and-effective-point","slug":"rethinking-efficient-and-effective-point","title":"Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba","date":"2024-05-09","arxiv_id":"2405.06116","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rethinking-efficient-and-effective-point#ran","syntology_url":"https://syntology.ai/paper/2405.06116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06116"}},"official":{"repos":["rhwxmx/eventmamba"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cofinal-enhancing-action-quality-assessment","slug":"cofinal-enhancing-action-quality-assessment","title":"CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment","date":"2024-04-22","arxiv_id":"2404.13999","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cofinal-enhancing-action-quality-assessment#ran","syntology_url":"https://syntology.ai/paper/2404.13999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13999"}},"official":{"repos":["zhoukanglei/cofinal_aqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-temporal-contextualization-for","slug":"leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","arxiv_id":"2404.09490","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leveraging-temporal-contextualization-for#ran","syntology_url":"https://syntology.ai/paper/2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}},"official":{"repos":["naver-ai/tc-clip"],"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/in-my-perspective-in-my-hands-accurate","slug":"in-my-perspective-in-my-hands-accurate","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","date":"2024-04-14","arxiv_id":"2404.09308","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":5,"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/in-my-perspective-in-my-hands-accurate#ran","syntology_url":"https://syntology.ai/paper/2404.09308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09308"}},"official":{"repos":["wiktormucha/effhandegonet"],"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/tim-a-time-interval-machine-for-audio-visual","slug":"tim-a-time-interval-machine-for-audio-visual","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","date":"2024-04-08","arxiv_id":"2404.05559","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tim-a-time-interval-machine-for-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2404.05559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05559"}},"official":{"repos":["jacobchalk/tim"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/disentangled-pre-training-for-human-object","slug":"disentangled-pre-training-for-human-object","title":"Disentangled Pre-training for Human-Object Interaction Detection","date":"2024-04-02","arxiv_id":"2404.01725","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"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, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/disentangled-pre-training-for-human-object#ran","syntology_url":"https://syntology.ai/paper/2404.01725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01725"}},"official":{"repos":["xingaoli/dp-hoi"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prego-online-mistake-detection-in-procedural","slug":"prego-online-mistake-detection-in-procedural","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","date":"2024-04-02","arxiv_id":"2404.01933","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prego-online-mistake-detection-in-procedural#ran","syntology_url":"https://syntology.ai/paper/2404.01933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01933"}},"official":{"repos":["aleflabo/prego"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/omnivid-a-generative-framework-for-universal","slug":"omnivid-a-generative-framework-for-universal","title":"OmniVid: A Generative Framework for Universal Video Understanding","date":"2024-03-26","arxiv_id":"2403.17935","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":11,"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/omnivid-a-generative-framework-for-universal#ran","syntology_url":"https://syntology.ai/paper/2403.17935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17935"}},"official":{"repos":["wangjk666/omnivid"],"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/benchmarks-and-challenges-in-pose-estimation","slug":"benchmarks-and-challenges-in-pose-estimation","title":"Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects","date":"2024-03-25","arxiv_id":"2403.16428","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":14,"phrase":"11 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/benchmarks-and-challenges-in-pose-estimation#ran","syntology_url":"https://syntology.ai/paper/2403.16428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16428"}},"official":{"repos":["facebookresearch/assemblyhands-toolkit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/understanding-long-videos-in-one-multimodal","slug":"understanding-long-videos-in-one-multimodal","title":"Understanding Long Videos with Multimodal Language Models","date":"2024-03-25","arxiv_id":"2403.16998","repositories_listed":1,"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":1,"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/understanding-long-videos-in-one-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.16998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16998"}},"official":{"repos":["kahnchana/mvu"],"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":["found_in_text","official"]}}},{"url":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","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":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) · 1 unverified","sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}},"official":{"repos":["mlvlab/vid-tldr"],"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/a-lie-group-approach-to-riemannian-batch","slug":"a-lie-group-approach-to-riemannian-batch","title":"A Lie Group Approach to Riemannian Batch Normalization","date":"2024-03-17","arxiv_id":"2403.11261","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-lie-group-approach-to-riemannian-batch#ran","syntology_url":"https://syntology.ai/paper/2403.11261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11261"}},"official":{"repos":["gitzh-chen/liebn"],"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/eventrpg-event-data-augmentation-with","slug":"eventrpg-event-data-augmentation-with","title":"EventRPG: Event Data Augmentation with Relevance Propagation Guidance","date":"2024-03-14","arxiv_id":"2403.09274","repositories_listed":1,"syntology":{"n":16,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":11,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/eventrpg-event-data-augmentation-with#ran","syntology_url":"https://syntology.ai/paper/2403.09274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09274"}},"official":{"repos":["myuansun/eventrpg"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/skateformer-skeletal-temporal-transformer-for","slug":"skateformer-skeletal-temporal-transformer-for","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","date":"2024-03-14","arxiv_id":"2403.09508","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/skateformer-skeletal-temporal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2403.09508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09508"}},"official":{"repos":["KAIST-VICLab/SkateFormer"],"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/on-the-utility-of-3d-hand-poses-for-action","slug":"on-the-utility-of-3d-hand-poses-for-action","title":"On the Utility of 3D Hand Poses for Action Recognition","date":"2024-03-14","arxiv_id":"2403.09805","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/on-the-utility-of-3d-hand-poses-for-action#ran","syntology_url":"https://syntology.ai/paper/2403.09805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09805"}},"official":{"repos":["s-shamil/HandFormer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-micro-action-recognition-dataset","slug":"benchmarking-micro-action-recognition-dataset","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","date":"2024-03-08","arxiv_id":"2403.05234","repositories_listed":1,"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/benchmarking-micro-action-recognition-dataset#ran","syntology_url":"https://syntology.ai/paper/2403.05234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05234"}},"official":{"repos":["vut-hfut/micro-action"],"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/mamba-nd-selective-state-space-modeling-for","slug":"mamba-nd-selective-state-space-modeling-for","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","date":"2024-02-08","arxiv_id":"2402.05892","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"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) · 2 unverified","sample_list":"/paper/mamba-nd-selective-state-space-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2402.05892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05892"}},"official":{"repos":["jacklishufan/mamba-nd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-adversarial-transferability-across","slug":"boosting-adversarial-transferability-across","title":"Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping","date":"2024-02-06","arxiv_id":"2402.03951","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/boosting-adversarial-transferability-across#ran","syntology_url":"https://syntology.ai/paper/2402.03951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03951"}},"official":{"repos":["linqinliang/decowa"],"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":["found_in_text"]}}},{"url":"/paper/taylor-videos-for-action-recognition","slug":"taylor-videos-for-action-recognition","title":"Taylor Videos for Action Recognition","date":"2024-02-05","arxiv_id":"2402.03019","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":3,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":8,"n_pointer_only":15,"phrase":"12 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/taylor-videos-for-action-recognition#ran","syntology_url":"https://syntology.ai/paper/2402.03019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03019"}},"official":{"repos":["leiwangr/video-ar"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":3,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-mutual-excitation-for-hand-to-hand","slug":"learning-mutual-excitation-for-hand-to-hand","title":"Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition","date":"2024-02-04","arxiv_id":"2402.02431","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-mutual-excitation-for-hand-to-hand#ran","syntology_url":"https://syntology.ai/paper/2402.02431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02431"}},"official":{"repos":["nkliuyifang/me-gcn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explore-human-parsing-modality-for-action-1","slug":"explore-human-parsing-modality-for-action-1","title":"Explore Human Parsing Modality for Action Recognition","date":"2024-01-04","arxiv_id":"2401.02138","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/explore-human-parsing-modality-for-action-1#ran","syntology_url":"https://syntology.ai/paper/2401.02138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02138"}},"official":{"repos":["liujf69/EPP-Net-Action"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ez-clip-efficient-zeroshot-video-action","slug":"ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","arxiv_id":"2312.08010","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"9 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ez-clip-efficient-zeroshot-video-action#ran","syntology_url":"https://syntology.ai/paper/2312.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08010"}},"official":{"repos":["shahzadnit/ez-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/x4d-sceneformer-enhanced-scene-understanding","slug":"x4d-sceneformer-enhanced-scene-understanding","title":"X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer","date":"2023-12-12","arxiv_id":"2312.07378","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/x4d-sceneformer-enhanced-scene-understanding#ran","syntology_url":"https://syntology.ai/paper/2312.07378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07378"}},"official":{"repos":["jinglinglingling/x4d"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/navigating-open-set-scenarios-for-skeleton","slug":"navigating-open-set-scenarios-for-skeleton","title":"Navigating Open Set Scenarios for Skeleton-based Action Recognition","date":"2023-12-11","arxiv_id":"2312.06330","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"8 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/navigating-open-set-scenarios-for-skeleton#ran","syntology_url":"https://syntology.ai/paper/2312.06330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06330"}},"official":{"repos":["kpeng9510/os-sar"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/step-catformer-spatial-temporal-effective","slug":"step-catformer-spatial-temporal-effective","title":"STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition","date":"2023-12-06","arxiv_id":"2312.03288","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":6,"phrase":"11 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/step-catformer-spatial-temporal-effective#ran","syntology_url":"https://syntology.ai/paper/2312.03288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03288"}},"official":{"repos":["maclong01/STEP-CATFormer"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hulk-a-universal-knowledge-translator-for","slug":"hulk-a-universal-knowledge-translator-for","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","date":"2023-12-04","arxiv_id":"2312.01697","repositories_listed":2,"syntology":{"n":24,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":11,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/hulk-a-universal-knowledge-translator-for#ran","syntology_url":"https://syntology.ai/paper/2312.01697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01697"}},"official":{"repos":["opengvlab/hulk","opengvlab/humanbench"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/cast-cross-attention-in-space-and-time-for-1","slug":"cast-cross-attention-in-space-and-time-for-1","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","date":"2023-11-30","arxiv_id":"2311.18825","repositories_listed":1,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":17,"phrase":"11 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/cast-cross-attention-in-space-and-time-for-1#ran","syntology_url":"https://syntology.ai/paper/2311.18825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18825"}},"official":null}},{"url":"/paper/learning-human-action-recognition","slug":"learning-human-action-recognition","title":"Learning Human Action Recognition Representations Without Real Humans","date":"2023-11-10","arxiv_id":"2311.06231","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":3,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"7 ran (of which 3 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) · 1 unverified","sample_list":"/paper/learning-human-action-recognition#ran","syntology_url":"https://syntology.ai/paper/2311.06231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06231"}},"official":{"repos":["howardzh01/ppma"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/industreal-a-dataset-for-procedure-step","slug":"industreal-a-dataset-for-procedure-step","title":"IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting","date":"2023-10-26","arxiv_id":"2310.17323","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":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) · 1 unverified","sample_list":"/paper/industreal-a-dataset-for-procedure-step#ran","syntology_url":"https://syntology.ai/paper/2310.17323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17323"}},"official":{"repos":["timschoonbeek/industreal"],"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/frozen-transformers-in-language-models-are","slug":"frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","arxiv_id":"2310.12973","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/frozen-transformers-in-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.12973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12973"}},"official":{"repos":["ziqipang/lm4visualencoding"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-beats-diffusion-tokenizer-is","slug":"language-model-beats-diffusion-tokenizer-is","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","date":"2023-10-09","arxiv_id":"2310.05737","repositories_listed":3,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":17,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":4,"n_no_contract":11,"n_pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 4 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-model-beats-diffusion-tokenizer-is#ran","syntology_url":"https://syntology.ai/paper/2310.05737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05737"}},"official":null}},{"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/cdfsl-v-cross-domain-few-shot-learning-for","slug":"cdfsl-v-cross-domain-few-shot-learning-for","title":"CDFSL-V: Cross-Domain Few-Shot Learning for Videos","date":"2023-09-07","arxiv_id":"2309.03989","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":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cdfsl-v-cross-domain-few-shot-learning-for#ran","syntology_url":"https://syntology.ai/paper/2309.03989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03989"}},"official":{"repos":["sarinda251/cdfsl-v"],"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/soar-scene-debiasing-open-set-action-1","slug":"soar-scene-debiasing-open-set-action-1","title":"SOAR: Scene-debiasing Open-set Action Recognition","date":"2023-09-03","arxiv_id":"2309.01265","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/soar-scene-debiasing-open-set-action-1#ran","syntology_url":"https://syntology.ai/paper/2309.01265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01265"}},"official":{"repos":["yhZhai/SOAR"],"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":["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/mofo-motion-focused-self-supervision-for","slug":"mofo-motion-focused-self-supervision-for","title":"MOFO: MOtion FOcused Self-Supervision for Video Understanding","date":"2023-08-23","arxiv_id":"2308.12447","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/mofo-motion-focused-self-supervision-for#ran","syntology_url":"https://syntology.ai/paper/2308.12447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12447"}},"official":{"repos":["moohnai/mofo"],"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/are-current-long-term-video-understanding","slug":"are-current-long-term-video-understanding","title":"Are current long-term video understanding datasets long-term?","date":"2023-08-22","arxiv_id":"2308.11244","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/are-current-long-term-video-understanding#ran","syntology_url":"https://syntology.ai/paper/2308.11244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11244"}},"official":{"repos":["ombretta/longterm_datasets"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ske2grid-skeleton-to-grid-representation","slug":"ske2grid-skeleton-to-grid-representation","title":"Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition","date":"2023-08-15","arxiv_id":"2308.07571","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ske2grid-skeleton-to-grid-representation#ran","syntology_url":"https://syntology.ai/paper/2308.07571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07571"}},"official":{"repos":["osvai/ske2grid"],"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/masked-motion-predictors-are-strong-3d-action","slug":"masked-motion-predictors-are-strong-3d-action","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","date":"2023-08-14","arxiv_id":"2308.07092","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/masked-motion-predictors-are-strong-3d-action#ran","syntology_url":"https://syntology.ai/paper/2308.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07092"}},"official":{"repos":["maoyunyao/mamp"],"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/hard-no-box-adversarial-attack-on-skeleton","slug":"hard-no-box-adversarial-attack-on-skeleton","title":"Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient","date":"2023-08-10","arxiv_id":"2308.05681","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/hard-no-box-adversarial-attack-on-skeleton#ran","syntology_url":"https://syntology.ai/paper/2308.05681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05681"}},"official":{"repos":["luyg45/hardnoboxattack"],"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"]}}},{"url":"/paper/temporally-adaptive-models-for-efficient","slug":"temporally-adaptive-models-for-efficient","title":"Temporally-Adaptive Models for Efficient Video Understanding","date":"2023-08-10","arxiv_id":"2308.05787","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":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/temporally-adaptive-models-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2308.05787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05787"}},"official":{"repos":["alibaba-mmai-research/TAdaConv"],"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/human-centric-scene-understanding-for-3d-1","slug":"human-centric-scene-understanding-for-3d-1","title":"Human-centric Scene Understanding for 3D Large-scale Scenarios","date":"2023-07-26","arxiv_id":"2307.14392","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":3,"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/human-centric-scene-understanding-for-3d-1#ran","syntology_url":"https://syntology.ai/paper/2307.14392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14392"}},"official":{"repos":["4dvlab/hucenlife"],"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/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/interactive-spatiotemporal-token-attention","slug":"interactive-spatiotemporal-token-attention","title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","date":"2023-07-14","arxiv_id":"2307.07469","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":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/interactive-spatiotemporal-token-attention#ran","syntology_url":"https://syntology.ai/paper/2307.07469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07469"}},"official":{"repos":["Necolizer/ISTA-Net"],"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/multimodal-distillation-for-egocentric-action","slug":"multimodal-distillation-for-egocentric-action","title":"Multimodal Distillation for Egocentric Action Recognition","date":"2023-07-14","arxiv_id":"2307.07483","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/multimodal-distillation-for-egocentric-action#ran","syntology_url":"https://syntology.ai/paper/2307.07483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07483"}},"official":{"repos":["gorjanradevski/multimodal-distillation"],"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/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/ha-vid-a-human-assembly-video-dataset-for","slug":"ha-vid-a-human-assembly-video-dataset-for","title":"HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding","date":"2023-07-09","arxiv_id":"2307.05721","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ha-vid-a-human-assembly-video-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2307.05721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05721"}},"official":{"repos":["iai-hrc/ha-vid"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["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/humans-in-4d-reconstructing-and-tracking","slug":"humans-in-4d-reconstructing-and-tracking","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","date":"2023-05-31","arxiv_id":"2305.20091","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/humans-in-4d-reconstructing-and-tracking#ran","syntology_url":"https://syntology.ai/paper/2305.20091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20091"}},"official":{"repos":["shubham-goel/4D-Humans"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/overcoming-topology-agnosticism-enhancing","slug":"overcoming-topology-agnosticism-enhancing","title":"Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness","date":"2023-05-19","arxiv_id":"2305.11468","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":9,"phrase":"11 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/overcoming-topology-agnosticism-enhancing#ran","syntology_url":"https://syntology.ai/paper/2305.11468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11468"}},"official":{"repos":["zhouyuxuanyx/blockgcn"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/riemannian-multiclass-logistics-regression","slug":"riemannian-multiclass-logistics-regression","title":"Riemannian Multinomial Logistics Regression for SPD Neural Networks","date":"2023-05-18","arxiv_id":"2305.11288","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/riemannian-multiclass-logistics-regression#ran","syntology_url":"https://syntology.ai/paper/2305.11288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11288"}},"official":{"repos":["gitzh-chen/spdmlr"],"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/mm-fi-multi-modal-non-intrusive-4d-human-1","slug":"mm-fi-multi-modal-non-intrusive-4d-human-1","title":"MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing","date":"2023-05-12","arxiv_id":"2305.10345","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/mm-fi-multi-modal-non-intrusive-4d-human-1#ran","syntology_url":"https://syntology.ai/paper/2305.10345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10345"}},"official":{"repos":["ybhbingo/mmfi_dataset"],"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/part-aware-contrastive-learning-for-self","slug":"part-aware-contrastive-learning-for-self","title":"Part Aware Contrastive Learning for Self-Supervised Action Recognition","date":"2023-05-01","arxiv_id":"2305.00666","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"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) · 6 unverified","sample_list":"/paper/part-aware-contrastive-learning-for-self#ran","syntology_url":"https://syntology.ai/paper/2305.00666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00666"}},"official":{"repos":["githubofhyl97/skeattnclr"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"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/robust-cross-modal-knowledge-distillation-for","slug":"robust-cross-modal-knowledge-distillation-for","title":"Robust Cross-Modal Knowledge Distillation for Unconstrained Videos","date":"2023-04-16","arxiv_id":"2304.07775","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":3,"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/robust-cross-modal-knowledge-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2304.07775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07775"}},"official":{"repos":["gewu-lab/cross-modal-distillation"],"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/vita-clip-video-and-text-adaptive-clip-via","slug":"vita-clip-video-and-text-adaptive-clip-via","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","date":"2023-04-06","arxiv_id":"2304.03307","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"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) · 4 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/vita-clip-video-and-text-adaptive-clip-via#ran","syntology_url":"https://syntology.ai/paper/2304.03307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03307"}},"official":{"repos":["talalwasim/vita-clip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/halp-hallucinating-latent-positives-for","slug":"halp-hallucinating-latent-positives-for","title":"HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions","date":"2023-04-01","arxiv_id":"2304.00387","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/halp-hallucinating-latent-positives-for#ran","syntology_url":"https://syntology.ai/paper/2304.00387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00387"}},"official":{"repos":["anshulbshah/halp"],"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/videomae-v2-scaling-video-masked-autoencoders","slug":"videomae-v2-scaling-video-masked-autoencoders","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","date":"2023-03-29","arxiv_id":"2303.16727","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":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) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}},"official":{"repos":["OpenGVLab/VideoMAEv2"],"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/unmasked-teacher-towards-training-efficient","slug":"unmasked-teacher-towards-training-efficient","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","date":"2023-03-28","arxiv_id":"2303.16058","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}},"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enlarging-instance-specific-and-class","slug":"enlarging-instance-specific-and-class","title":"Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition","date":"2023-03-25","arxiv_id":"2303.15467","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/enlarging-instance-specific-and-class#ran","syntology_url":"https://syntology.ai/paper/2303.15467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15467"}},"official":{"repos":["jun-cen/psl"],"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/augmenting-and-aligning-snippets-for-few-shot","slug":"augmenting-and-aligning-snippets-for-few-shot","title":"Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation","date":"2023-03-18","arxiv_id":"2303.10451","repositories_listed":0,"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/augmenting-and-aligning-snippets-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2303.10451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10451"}},"official":null}},{"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/hyperbolic-self-paced-learning-for-self","slug":"hyperbolic-self-paced-learning-for-self","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","date":"2023-03-10","arxiv_id":"2303.06242","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":9,"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) · 9 unverified","sample_list":"/paper/hyperbolic-self-paced-learning-for-self#ran","syntology_url":"https://syntology.ai/paper/2303.06242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06242"}},"official":{"repos":["paolomandica/hysp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-discriminative-representations-for-4","slug":"learning-discriminative-representations-for-4","title":"Learning Discriminative Representations for Skeleton Based Action Recognition","date":"2023-03-07","arxiv_id":"2303.03729","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/learning-discriminative-representations-for-4#ran","syntology_url":"https://syntology.ai/paper/2303.03729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03729"}},"official":{"repos":["zhysora/fr-head"],"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/clip-guided-prototype-modulating-for-few-shot","slug":"clip-guided-prototype-modulating-for-few-shot","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","date":"2023-03-06","arxiv_id":"2303.02982","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-guided-prototype-modulating-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2303.02982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02982"}},"official":{"repos":["alibaba-mmai-research/clip-fsar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-action-representation","slug":"self-supervised-action-representation","title":"Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences","date":"2023-02-17","arxiv_id":"2302.09018","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/self-supervised-action-representation#ran","syntology_url":"https://syntology.ai/paper/2302.09018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.09018"}},"official":{"repos":["yujieouo/pstl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hiervl-learning-hierarchical-video-language","slug":"hiervl-learning-hierarchical-video-language","title":"HierVL: Learning Hierarchical Video-Language Embeddings","date":"2023-01-05","arxiv_id":"2301.02311","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hiervl-learning-hierarchical-video-language#ran","syntology_url":"https://syntology.ai/paper/2301.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02311"}},"official":null}},{"url":"/paper/tempclr-temporal-alignment-representation","slug":"tempclr-temporal-alignment-representation","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","date":"2022-12-28","arxiv_id":"2212.13738","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/tempclr-temporal-alignment-representation#ran","syntology_url":"https://syntology.ai/paper/2212.13738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13738"}},"official":{"repos":["yyuncong/tempclr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/chairs-towards-full-body-articulated-human","slug":"chairs-towards-full-body-articulated-human","title":"Full-Body Articulated Human-Object Interaction","date":"2022-12-20","arxiv_id":"2212.10621","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/chairs-towards-full-body-articulated-human#ran","syntology_url":"https://syntology.ai/paper/2212.10621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10621"}},"official":{"repos":["jnnan/chairs"],"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/learning-video-representations-from-large","slug":"learning-video-representations-from-large","title":"Learning Video Representations from Large Language Models","date":"2022-12-08","arxiv_id":"2212.04501","repositories_listed":3,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":20,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-video-representations-from-large#ran","syntology_url":"https://syntology.ai/paper/2212.04501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04501"}},"official":{"repos":["facebookresearch/lavila"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","repositories_listed":2,"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/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}},"official":{"repos":["opengvlab/internvideo"],"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/rethinking-video-vits-sparse-video-tubes-for","slug":"rethinking-video-vits-sparse-video-tubes-for","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","date":"2022-12-06","arxiv_id":"2212.03229","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}},"official":null}},{"url":"/paper/resformer-scaling-vits-with-multi-resolution","slug":"resformer-scaling-vits-with-multi-resolution","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","date":"2022-12-01","arxiv_id":"2212.00776","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/resformer-scaling-vits-with-multi-resolution#ran","syntology_url":"https://syntology.ai/paper/2212.00776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00776"}},"official":{"repos":["ruitian12/resformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-good-practices-for-missing-modality","slug":"towards-good-practices-for-missing-modality","title":"Towards Good Practices for Missing Modality Robust Action Recognition","date":"2022-11-25","arxiv_id":"2211.13916","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/towards-good-practices-for-missing-modality#ran","syntology_url":"https://syntology.ai/paper/2211.13916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13916"}},"official":{"repos":["sangminwoo/actionmae"],"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/efficient-video-representation-learning-via","slug":"efficient-video-representation-learning-via","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","date":"2022-11-19","arxiv_id":"2211.10636","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"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) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-video-representation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2211.10636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10636"}},"official":{"repos":["sunilhoho/everest","sunilhoho/VideoMS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"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/hypergraph-transformer-for-skeleton-based","slug":"hypergraph-transformer-for-skeleton-based","title":"Hypergraph Transformer for Skeleton-based Action Recognition","date":"2022-11-17","arxiv_id":"2211.09590","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":9,"phrase":"11 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hypergraph-transformer-for-skeleton-based#ran","syntology_url":"https://syntology.ai/paper/2211.09590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09590"}},"official":{"repos":["ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/eva-exploring-the-limits-of-masked-visual","slug":"eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","arxiv_id":"2211.07636","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}},"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-dtw-for-time-series-and-sequences","slug":"uncertainty-dtw-for-time-series-and-sequences","title":"Uncertainty-DTW for Time Series and Sequences","date":"2022-10-30","arxiv_id":"2211.00005","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/uncertainty-dtw-for-time-series-and-sequences#ran","syntology_url":"https://syntology.ai/paper/2211.00005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00005"}},"official":{"repos":["leiwangr/udtw"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/motionbert-unified-pretraining-for-human","slug":"motionbert-unified-pretraining-for-human","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","date":"2022-10-12","arxiv_id":"2210.06551","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/motionbert-unified-pretraining-for-human#ran","syntology_url":"https://syntology.ai/paper/2210.06551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06551"}},"official":{"repos":["Walter0807/MotionBERT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"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/learning-state-aware-visual-representations","slug":"learning-state-aware-visual-representations","title":"Learning State-Aware Visual Representations from Audible Interactions","date":"2022-09-27","arxiv_id":"2209.13583","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-state-aware-visual-representations#ran","syntology_url":"https://syntology.ai/paper/2209.13583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.13583"}},"official":{"repos":["HimangiM/RepLAI"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-dataset-training-of-transformers-for","slug":"multi-dataset-training-of-transformers-for","title":"Multi-dataset Training of Transformers for Robust Action Recognition","date":"2022-09-26","arxiv_id":"2209.12362","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":0,"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/multi-dataset-training-of-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2209.12362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12362"}},"official":{"repos":["junweiliang/multitrain"],"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"]}}}],"record_sha256":"e0ee8f5d7f5918b1116fe5634c3c25dca78baa1ba98bf6ae1334a202d73e7b92","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}