{"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/2","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":"archive","order_definition":"date (newest first), then slug","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":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,171],"of":171,"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","prev":"/dataset/kinetics","next":null,"papers":[{"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/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/video-classification-with-finecoarse-networks","slug":"video-classification-with-finecoarse-networks","title":"Busy-Quiet Video Disentangling for Video Classification","date":"2021-03-29","arxiv_id":"2103.15584","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/an-image-is-worth-16x16-words-what-is-a-video","slug":"an-image-is-worth-16x16-words-what-is-a-video","title":"An Image is Worth 16x16 Words, What is a Video Worth?","date":"2021-03-25","arxiv_id":"2103.13915","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["Alibaba-MIIL/STAM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-image-is-worth-16x16-words-what-is-a-video#ran","syntology_url":"https://syntology.ai/paper/2103.13915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13915"}}}},{"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/predicting-video-with-vqvae-1","slug":"predicting-video-with-vqvae-1","title":"Predicting Video with VQVAE","date":"2021-03-02","arxiv_id":"2103.01950","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/video-transformer-network","slug":"video-transformer-network","title":"Video Transformer Network","date":"2021-02-01","arxiv_id":"2102.00719","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"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/mvfnet-multi-view-fusion-network-for","slug":"mvfnet-multi-view-fusion-network-for","title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","date":"2020-12-13","arxiv_id":"2012.06977","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pose-refinement-graph-convolutional-network","slug":"pose-refinement-graph-convolutional-network","title":"Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition","date":"2020-10-14","arxiv_id":"2010.07367","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/all-about-knowledge-graphs-for-actions","slug":"all-about-knowledge-graphs-for-actions","title":"All About Knowledge Graphs for Actions","date":"2020-08-28","arxiv_id":"2008.12432","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatial-temporal-transformer-network-for","slug":"spatial-temporal-transformer-network-for","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","date":"2020-08-17","arxiv_id":"2008.07404","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spatiotemporal-contrastive-video","slug":"spatiotemporal-contrastive-video","title":"Spatiotemporal Contrastive Video Representation Learning","date":"2020-08-09","arxiv_id":"2008.03800","rows_on_this_dataset":3,"code_links":4,"syntology":null},{"paper":"/paper/dynamic-gcn-context-enriched-topology","slug":"dynamic-gcn-context-enriched-topology","title":"Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition","date":"2020-07-29","arxiv_id":"2007.14690","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/region-based-non-local-operation-for-video","slug":"region-based-non-local-operation-for-video","title":"Region-based Non-local Operation for Video Classification","date":"2020-07-17","arxiv_id":"2007.09033","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/temporal-extension-module-for-skeleton-based-1","slug":"temporal-extension-module-for-skeleton-based-1","title":"Temporal Extension Module for Skeleton-Based Action Recognition","date":"2020-03-19","arxiv_id":"2003.08951","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/predictively-encoded-graph-convolutional","slug":"predictively-encoded-graph-convolutional","title":"Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition","date":"2020-03-17","arxiv_id":"2003.07514","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transformation-based-adversarial-video","slug":"transformation-based-adversarial-video","title":"Transformation-based Adversarial Video Prediction on Large-Scale Data","date":"2020-03-09","arxiv_id":"2003.04035","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/centrality-graph-convolutional-networks-for","slug":"centrality-graph-convolutional-networks-for","title":"Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition","date":"2020-03-06","arxiv_id":"2003.03007","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/skeleton-based-action-recognition-with-multi","slug":"skeleton-based-action-recognition-with-multi","title":"Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks","date":"2019-12-15","arxiv_id":"1912.06971","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"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/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/an-attention-enhanced-recurrent-graph","slug":"an-attention-enhanced-recurrent-graph","title":"An Attention-Enhanced Recurrent Graph Convolutional Network for Skeleton-Based Action Recognition","date":"2019-11-27","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/190807625","slug":"190807625","title":"Action recognition with spatial-temporal discriminative filter banks","date":"2019-08-20","arxiv_id":"1908.07625","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/stm-spatiotemporal-and-motion-encoding-for","slug":"stm-spatiotemporal-and-motion-encoding-for","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","date":"2019-08-07","arxiv_id":"1908.02486","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/two-stream-video-classification-with-cross","slug":"two-stream-video-classification-with-cross","title":"Two-Stream Video Classification with Cross-Modality Attention","date":"2019-08-01","arxiv_id":"1908.00497","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatiotemporal-graph-routing-for-skeleton","slug":"spatiotemporal-graph-routing-for-skeleton","title":"Spatiotemporal graph routing for skeleton-based action recognition","date":"2019-07-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-video-generation-on-complex","slug":"efficient-video-generation-on-complex","title":"Adversarial Video Generation on Complex Datasets","date":"2019-07-15","arxiv_id":"1907.06571","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/learning-spatio-temporal-representation-with-3","slug":"learning-spatio-temporal-representation-with-3","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","date":"2019-06-13","arxiv_id":"1906.05571","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/faster-recurrent-networks-for-video","slug":"faster-recurrent-networks-for-video","title":"FASTER Recurrent Networks for Efficient Video Classification","date":"2019-06-10","arxiv_id":"1906.04226","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/video-modeling-with-correlation-networks","slug":"video-modeling-with-correlation-networks","title":"Video Modeling with Correlation Networks","date":"2019-06-07","arxiv_id":"1906.03349","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/scaling-autoregressive-video-models","slug":"scaling-autoregressive-video-models","title":"Scaling Autoregressive Video Models","date":"2019-06-06","arxiv_id":"1906.02634","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/190600550","slug":"190600550","title":"Global Textual Relation Embedding for Relational Understanding","date":"2019-06-03","arxiv_id":"1906.00550","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/collaborative-spatiotemporal-feature-learning","slug":"collaborative-spatiotemporal-feature-learning","title":"Collaborative Spatiotemporal Feature Learning for Video Action Recognition","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mars-motion-augmented-rgb-stream-for-action","slug":"mars-motion-augmented-rgb-stream-for-action","title":"MARS: Motion-Augmented RGB Stream for Action Recognition","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/skeleton-based-action-recognition-with-4","slug":"skeleton-based-action-recognition-with-4","title":"Skeleton-Based Action Recognition With Directed Graph Neural Networks","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/holistic-large-scale-video-understanding","slug":"holistic-large-scale-video-understanding","title":"Large Scale Holistic Video Understanding","date":"2019-04-25","arxiv_id":"1904.11451","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/d3d-distilled-3d-networks-for-video-action","slug":"d3d-distilled-3d-networks-for-video-action","title":"D3D: Distilled 3D Networks for Video Action Recognition","date":"2018-12-19","arxiv_id":"1812.08249","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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/evolving-space-time-neural-architectures-for","slug":"evolving-space-time-neural-architectures-for","title":"Evolving Space-Time Neural Architectures for Videos","date":"2018-11-26","arxiv_id":"1811.10636","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/skeleton-based-action-recognition-with","slug":"skeleton-based-action-recognition-with","title":"Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention","date":"2018-11-10","arxiv_id":"1811.04237","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a2-nets-double-attention-networks","slug":"a2-nets-double-attention-networks","title":"$A^2$-Nets: Double Attention Networks","date":"2018-10-27","arxiv_id":"1810.11579","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/representation-flow-for-action-recognition","slug":"representation-flow-for-action-recognition","title":"Representation Flow for Action Recognition","date":"2018-10-02","arxiv_id":"1810.01455","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/multi-fiber-networks-for-video-recognition","slug":"multi-fiber-networks-for-video-recognition","title":"Multi-Fiber Networks for Video Recognition","date":"2018-07-30","arxiv_id":"1807.11195","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rethinking-spatiotemporal-feature-learning","slug":"rethinking-spatiotemporal-feature-learning","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","date":"2017-12-13","arxiv_id":"1712.04851","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"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/appearance-and-relation-networks-for-video","slug":"appearance-and-relation-networks-for-video","title":"Appearance-and-Relation Networks for Video Classification","date":"2017-11-24","arxiv_id":"1711.09125","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/convnet-architecture-search-for","slug":"convnet-architecture-search-for","title":"ConvNet Architecture Search for Spatiotemporal Feature Learning","date":"2017-08-16","arxiv_id":"1708.05038","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revisiting-the-effectiveness-of-off-the-shelf","slug":"revisiting-the-effectiveness-of-off-the-shelf","title":"Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification","date":"2017-08-12","arxiv_id":"1708.03805","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/learning-a-deep-embedding-model-for-zero-shot","slug":"learning-a-deep-embedding-model-for-zero-shot","title":"Learning a Deep Embedding Model for Zero-Shot Learning","date":"2016-11-15","arxiv_id":"1611.05088","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"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"}}}},{"paper":"/paper/an-embarrassingly-simple-approach-to-zero","slug":"an-embarrassingly-simple-approach-to-zero","title":"An embarrassingly simple approach to zero-shot learning","date":"2015-07-06","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/label-embedding-for-image-classification","slug":"label-embedding-for-image-classification","title":"Label-Embedding for Image Classification","date":"2015-03-30","arxiv_id":"1503.08677","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/evaluation-of-output-embeddings-for-fine","slug":"evaluation-of-output-embeddings-for-fine","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","date":"2014-09-30","arxiv_id":"1409.8403","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/devise-a-deep-visual-semantic-embedding-model","slug":"devise-a-deep-visual-semantic-embedding-model","title":"DeViSE: A Deep Visual-Semantic Embedding Model","date":"2013-12-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"record_sha256":"01345c2100a9e801bae7244eefe0521df39ea137b416495de184ec56b44c894c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}