{"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":"/dataset/kinetics/papers/ran/1","list_of":"/dataset/kinetics","dataset":"Kinetics","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_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'","samples_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)"},"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 dataset or check it against this dataset'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.","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,73],"of":73,"counts":{"papers_with_a_benchmark_row":171,"with_a_code_link":132,"where_syntology_ran_a_sample":73,"not_listed_spam_title":0,"listed":171,"listed_where_code_ran":73,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":66,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":66,"listed_every_run_a_failure_of_syntologys_instrument":7,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/kinetics/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/make-your-training-flexible-towards","slug":"make-your-training-flexible-towards","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","date":"2025-03-18","arxiv_id":"2503.14237","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}}}},{"paper":"/paper/larp-tokenizing-videos-with-a-learned-1","slug":"larp-tokenizing-videos-with-a-learned-1","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","date":"2024-10-28","arxiv_id":"2410.21264","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/larp-tokenizing-videos-with-a-learned-1#ran","syntology_url":"https://syntology.ai/paper/2410.21264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21264"}}}},{"paper":"/paper/omnitokenizer-a-joint-image-video-tokenizer","slug":"omnitokenizer-a-joint-image-video-tokenizer","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","date":"2024-06-13","arxiv_id":"2406.09399","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["foundationvision/omnitokenizer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/omnitokenizer-a-joint-image-video-tokenizer#ran","syntology_url":"https://syntology.ai/paper/2406.09399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09399"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/videomamba-state-space-model-for-efficient","slug":"videomamba-state-space-model-for-efficient","title":"VideoMamba: State Space Model for Efficient Video Understanding","date":"2024-03-11","arxiv_id":"2403.06977","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":5,"samples_ran_checked":6,"samples_ran_instrument_failed":3,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/videomamba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videomamba-state-space-model-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2403.06977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06977"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":17,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/ost-refining-text-knowledge-with-optimal","slug":"ost-refining-text-knowledge-with-optimal","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","date":"2023-11-30","arxiv_id":"2312.00096","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["tomchen-ctj/OST"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ost-refining-text-knowledge-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2312.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00096"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":20,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["pku-yuangroup/languagebind"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/orthogonal-temporal-interpolation-for-zero","slug":"orthogonal-temporal-interpolation-for-zero","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","date":"2023-08-14","arxiv_id":"2308.06897","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["sweetorangezhuyan/mm2023_oti"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/orthogonal-temporal-interpolation-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.06897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06897"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"paper":"/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","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":8,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"paper":"/paper/scalable-adaptive-computation-for-iterative","slug":"scalable-adaptive-computation-for-iterative","title":"Scalable Adaptive Computation for Iterative Generation","date":"2022-12-22","arxiv_id":"2212.11972","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":29,"samples_ran":21,"samples_constructed":9,"samples_ran_checked":18,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":1,"official":{"repos":["google-research/pix2seq"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":2,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scalable-adaptive-computation-for-iterative#ran","syntology_url":"https://syntology.ai/paper/2212.11972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11972"}}}},{"paper":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/magvit-masked-generative-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05199"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/adamae-adaptive-masking-for-efficient","slug":"adamae-adaptive-masking-for-efficient","title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","date":"2022-11-16","arxiv_id":"2211.09120","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":25,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":6,"official":{"repos":["wgcban/adamae"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/adamae-adaptive-masking-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2211.09120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09120"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/hierarchically-decomposed-graph-convolutional","slug":"hierarchically-decomposed-graph-convolutional","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2022-08-23","arxiv_id":"2208.10741","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["Jho-Yonsei/HD-GCN"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hierarchically-decomposed-graph-convolutional#ran","syntology_url":"https://syntology.ai/paper/2208.10741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10741"}}}},{"paper":"/paper/frozen-clip-models-are-efficient-video","slug":"frozen-clip-models-are-efficient-video","title":"Frozen CLIP Models are Efficient Video Learners","date":"2022-08-06","arxiv_id":"2208.03550","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":5,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":10,"official":{"repos":["opengvlab/efficient-video-recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/frozen-clip-models-are-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2208.03550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03550"}}}},{"paper":"/paper/expanding-language-image-pretrained-models","slug":"expanding-language-image-pretrained-models","title":"Expanding Language-Image Pretrained Models for General Video Recognition","date":"2022-08-04","arxiv_id":"2208.02816","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}}}},{"paper":"/paper/spatiotemporal-self-attention-modeling-with","slug":"spatiotemporal-self-attention-modeling-with","title":"Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition","date":"2022-07-27","arxiv_id":"2207.13259","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["martinxm/tps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spatiotemporal-self-attention-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2207.13259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13259"}}}},{"paper":"/paper/parameter-efficient-image-to-video-transfer","slug":"parameter-efficient-image-to-video-transfer","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","date":"2022-06-27","arxiv_id":"2206.13559","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["linziyi96/st-adapter"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/parameter-efficient-image-to-video-transfer#ran","syntology_url":"https://syntology.ai/paper/2206.13559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13559"}}}},{"paper":"/paper/diffusion-models-for-video-prediction-and","slug":"diffusion-models-for-video-prediction-and","title":"Diffusion Models for Video Prediction and Infilling","date":"2022-06-15","arxiv_id":"2206.07696","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":19,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":4,"samples_unverified":7,"pointer_only_for_licence":11,"official":{"repos":["Tobi-r9/RaMViD"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusion-models-for-video-prediction-and#ran","syntology_url":"https://syntology.ai/paper/2206.07696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07696"}}}},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/videomae-masked-autoencoders-are-data-1","slug":"videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","rows_on_this_dataset":5,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":12,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"paper":"/paper/direcformer-a-directed-attention-in","slug":"direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","arxiv_id":"2203.10233","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["uark-cviu/direcformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/direcformer-a-directed-attention-in#ran","syntology_url":"https://syntology.ai/paper/2203.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10233"}}}},{"paper":"/paper/omnivore-a-single-model-for-many-visual","slug":"omnivore-a-single-model-for-many-visual","title":"Omnivore: A Single Model for Many Visual Modalities","date":"2022-01-20","arxiv_id":"2201.08377","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}}}},{"paper":"/paper/nuwa-visual-synthesis-pre-training-for-neural","slug":"nuwa-visual-synthesis-pre-training-for-neural","title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","date":"2021-11-24","arxiv_id":"2111.12417","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/nuwa-visual-synthesis-pre-training-for-neural#ran","syntology_url":"https://syntology.ai/paper/2111.12417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12417"}}}},{"paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","slug":"swin-transformer-v2-scaling-up-capacity-and","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","date":"2021-11-18","arxiv_id":"2111.09883","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":30,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":0,"samples_unverified":13,"pointer_only_for_licence":4,"official":{"repos":["microsoft/Swin-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/swin-transformer-v2-scaling-up-capacity-and#ran","syntology_url":"https://syntology.ai/paper/2111.09883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09883"}}}},{"paper":"/paper/actionclip-a-new-paradigm-for-video-action","slug":"actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["sallymmx/actionclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/actionclip-a-new-paradigm-for-video-action#ran","syntology_url":"https://syntology.ai/paper/2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}}}},{"paper":"/paper/learning-multi-granular-spatio-temporal-graph","slug":"learning-multi-granular-spatio-temporal-graph","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","date":"2021-08-10","arxiv_id":"2108.04536","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["tailin1009/dualhead-network"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-multi-granular-spatio-temporal-graph#ran","syntology_url":"https://syntology.ai/paper/2108.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04536"}}}},{"paper":"/paper/elaborative-rehearsal-for-zero-shot-action","slug":"elaborative-rehearsal-for-zero-shot-action","title":"Elaborative Rehearsal for Zero-shot Action Recognition","date":"2021-08-05","arxiv_id":"2108.02833","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["DeLightCMU/ElaborativeRehearsal"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/elaborative-rehearsal-for-zero-shot-action#ran","syntology_url":"https://syntology.ai/paper/2108.02833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02833"}}}},{"paper":"/paper/ccvs-context-aware-controllable-video","slug":"ccvs-context-aware-controllable-video","title":"CCVS: Context-aware Controllable Video Synthesis","date":"2021-07-16","arxiv_id":"2107.08037","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["16lemoing/ccvs"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ccvs-context-aware-controllable-video#ran","syntology_url":"https://syntology.ai/paper/2107.08037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.08037"}}}},{"paper":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","rows_on_this_dataset":6,"code_links":15,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":32,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":5,"samples_unverified":13,"pointer_only_for_licence":7,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"paper":"/paper/vimpac-video-pre-training-via-masked-token","slug":"vimpac-video-pre-training-via-masked-token","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","date":"2021-06-21","arxiv_id":"2106.11250","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["airsplay/vimpac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vimpac-video-pre-training-via-masked-token#ran","syntology_url":"https://syntology.ai/paper/2106.11250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11250"}}}},{"paper":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","slug":"tokenlearner-what-can-8-learned-tokens-do-for","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","date":"2021-06-21","arxiv_id":"2106.11297","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":1,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-research/scenic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}}}},{"paper":"/paper/keeping-your-eye-on-the-ball-trajectory","slug":"keeping-your-eye-on-the-ball-trajectory","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","date":"2021-06-09","arxiv_id":"2106.05392","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["facebookresearch/Motionformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/keeping-your-eye-on-the-ball-trajectory#ran","syntology_url":"https://syntology.ai/paper/2106.05392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05392"}}}},{"paper":"/paper/ct-net-channel-tensorization-network-for-1","slug":"ct-net-channel-tensorization-network-for-1","title":"CT-Net: Channel Tensorization Network for Video Classification","date":"2021-06-03","arxiv_id":"2106.01603","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":7,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["Andy1621/CT-Net"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ct-net-channel-tensorization-network-for-1#ran","syntology_url":"https://syntology.ai/paper/2106.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01603"}}}},{"paper":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}},{"paper":"/paper/multiscale-vision-transformers","slug":"multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","rows_on_this_dataset":4,"code_links":8,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":26,"samples_ran":13,"samples_constructed":10,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":13,"pointer_only_for_licence":5,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"paper":"/paper/2103-15691","slug":"2103-15691","title":"ViViT: A Video Vision Transformer","date":"2021-03-29","arxiv_id":"2103.15691","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":10,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":1,"official":{"repos":["google-research/scenic"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}}}},{"paper":"/paper/movinets-mobile-video-networks-for-efficient","slug":"movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","arxiv_id":"2103.11511","rows_on_this_dataset":7,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":13,"samples_ran":9,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"paper":"/paper/is-space-time-attention-all-you-need-for","slug":"is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","arxiv_id":"2102.05095","rows_on_this_dataset":3,"code_links":16,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":43,"samples_ran":35,"samples_constructed":17,"samples_ran_checked":21,"samples_ran_instrument_failed":14,"samples_unverified":8,"pointer_only_for_licence":14,"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}}}},{"paper":"/paper/tdn-temporal-difference-networks-for","slug":"tdn-temporal-difference-networks-for","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","date":"2020-12-18","arxiv_id":"2012.10071","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["MCG-NJU/TDN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tdn-temporal-difference-networks-for#ran","syntology_url":"https://syntology.ai/paper/2012.10071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.10071"}}}},{"paper":"/paper/motionsqueeze-neural-motion-feature-learning","slug":"motionsqueeze-neural-motion-feature-learning","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","date":"2020-07-20","arxiv_id":"2007.09933","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/motionsqueeze-neural-motion-feature-learning#ran","syntology_url":"https://syntology.ai/paper/2007.09933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09933"}}}},{"paper":"/paper/latent-video-transformer","slug":"latent-video-transformer","title":"Latent Video Transformer","date":"2020-06-18","arxiv_id":"2006.10704","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["rakhimovv/lvt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/latent-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2006.10704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10704"}}}},{"paper":"/paper/x3d-expanding-architectures-for-efficient","slug":"x3d-expanding-architectures-for-efficient","title":"X3D: Expanding Architectures for Efficient Video Recognition","date":"2020-04-09","arxiv_id":"2004.04730","rows_on_this_dataset":4,"code_links":8,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}}}},{"paper":"/paper/disentangling-and-unifying-graph-convolutions","slug":"disentangling-and-unifying-graph-convolutions","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","date":"2020-03-31","arxiv_id":"2003.14111","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["kenziyuliu/ms-g3d"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/disentangling-and-unifying-graph-convolutions#ran","syntology_url":"https://syntology.ai/paper/2003.14111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.14111"}}}},{"paper":"/paper/omni-sourced-webly-supervised-learning-for","slug":"omni-sourced-webly-supervised-learning-for","title":"Omni-sourced Webly-supervised Learning for Video Recognition","date":"2020-03-29","arxiv_id":"2003.13042","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["open-mmlab/mmaction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}}}},{"paper":"/paper/more-is-less-learning-efficient-video-1","slug":"more-is-less-learning-efficient-video-1","title":"More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation","date":"2019-12-02","arxiv_id":"1912.00869","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["IBM/bLVNet-TAM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/more-is-less-learning-efficient-video-1#ran","syntology_url":"https://syntology.ai/paper/1912.00869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00869"}}}},{"paper":"/paper/a-multigrid-method-for-efficiently-training","slug":"a-multigrid-method-for-efficiently-training","title":"A Multigrid Method for Efficiently Training Video Models","date":"2019-12-02","arxiv_id":"1912.00998","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-multigrid-method-for-efficiently-training#ran","syntology_url":"https://syntology.ai/paper/1912.00998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00998"}}}},{"paper":"/paper/learning-graph-convolutional-network-for","slug":"learning-graph-convolutional-network-for","title":"Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching","date":"2019-11-11","arxiv_id":"1911.04131","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-graph-convolutional-network-for#ran","syntology_url":"https://syntology.ai/paper/1911.04131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04131"}}}},{"paper":"/paper/chirality-nets-for-human-pose-regression","slug":"chirality-nets-for-human-pose-regression","title":"Chirality Nets for Human Pose Regression","date":"2019-10-31","arxiv_id":"1911.00029","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chirality-nets-for-human-pose-regression#ran","syntology_url":"https://syntology.ai/paper/1911.00029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00029"}}}},{"paper":"/paper/what-makes-training-multi-modal-networks-hard","slug":"what-makes-training-multi-modal-networks-hard","title":"What Makes Training Multi-Modal Classification Networks Hard?","date":"2019-05-29","arxiv_id":"1905.12681","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/what-makes-training-multi-modal-networks-hard#ran","syntology_url":"https://syntology.ai/paper/1905.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12681"}}}},{"paper":"/paper/large-scale-weakly-supervised-pre-training","slug":"large-scale-weakly-supervised-pre-training","title":"Large-scale weakly-supervised pre-training for video action recognition","date":"2019-05-02","arxiv_id":"1905.00561","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":21,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/large-scale-weakly-supervised-pre-training#ran","syntology_url":"https://syntology.ai/paper/1905.00561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00561"}}}},{"paper":"/paper/actional-structural-graph-convolutional","slug":"actional-structural-graph-convolutional","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","date":"2019-04-26","arxiv_id":"1904.12659","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":18,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":5,"official":{"repos":["limaosen0/AS-GCN"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/actional-structural-graph-convolutional#ran","syntology_url":"https://syntology.ai/paper/1904.12659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12659"}}}},{"paper":"/paper/drop-an-octave-reducing-spatial-redundancy-in","slug":"drop-an-octave-reducing-spatial-redundancy-in","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","date":"2019-04-10","arxiv_id":"1904.05049","rows_on_this_dataset":1,"code_links":28,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":34,"samples_ran":24,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":13,"samples_unverified":10,"pointer_only_for_licence":9,"official":{"repos":["facebookresearch/OctConv"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/drop-an-octave-reducing-spatial-redundancy-in#ran","syntology_url":"https://syntology.ai/paper/1904.05049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05049"}}}},{"paper":"/paper/video-classification-with-channel-separated","slug":"video-classification-with-channel-separated","title":"Video Classification with Channel-Separated Convolutional Networks","date":"2019-04-04","arxiv_id":"1904.02811","rows_on_this_dataset":5,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["facebookresearch/VMZ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-classification-with-channel-separated#ran","syntology_url":"https://syntology.ai/paper/1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}}}},{"paper":"/paper/slowfast-networks-for-video-recognition","slug":"slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","rows_on_this_dataset":6,"code_links":15,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"paper":"/paper/temporal-shift-module-for-efficient-video","slug":"temporal-shift-module-for-efficient-video","title":"TSM: Temporal Shift Module for Efficient Video Understanding","date":"2018-11-20","arxiv_id":"1811.08383","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":16,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":6,"pointer_only_for_licence":6,"official":{"repos":["MIT-HAN-LAB/temporal-shift-module"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporal-shift-module-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/1811.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08383"}}}},{"paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","slug":"a-closer-look-at-spatiotemporal-convolutions","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","date":"2017-11-30","arxiv_id":"1711.11248","rows_on_this_dataset":6,"code_links":24,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"paper":"/paper/non-local-neural-networks","slug":"non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","arxiv_id":"1711.07971","rows_on_this_dataset":1,"code_links":32,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/video-nonlocal-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}}}},{"paper":"/paper/quo-vadis-action-recognition-a-new-model-and","slug":"quo-vadis-action-recognition-a-new-model-and","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","date":"2017-05-22","arxiv_id":"1705.07750","rows_on_this_dataset":1,"code_links":34,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":28,"samples_ran":16,"samples_constructed":7,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":12,"pointer_only_for_licence":7,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/quo-vadis-action-recognition-a-new-model-and#ran","syntology_url":"https://syntology.ai/paper/1705.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07750"}}}},{"paper":"/paper/temporal-segment-networks-towards-good","slug":"temporal-segment-networks-towards-good","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","date":"2016-08-02","arxiv_id":"1608.00859","rows_on_this_dataset":1,"code_links":22,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":24,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":14,"pointer_only_for_licence":3,"official":{"repos":["yjxiong/caffe","yjxiong/temporal-segment-networks"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/temporal-segment-networks-towards-good#ran","syntology_url":"https://syntology.ai/paper/1608.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.00859"}}}}],"record_sha256":"2a423a402a5f3ce4c7375c950339f30da005a5004c2340cadfccdf4ff8c99479","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}