{"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/sports-1m","name":"Sports-1M","full_name":null,"description_markdown":"The **Sports-1M** dataset consists of over a million videos from YouTube. The videos in the dataset can be obtained through the YouTube URL specified by the authors. Approximately 7% (as of 2016) of the videos have been removed by the YouTube uploaders since the dataset was compiled. However, there are still over a million videos in the dataset with 487 sports-related categories with 1,000 to 3,000 videos per category. The videos are automatically labelled with 487 sports classes using the YouTube Topics API by analyzing the text metadata associated with the videos (e.g. tags, descriptions). Approximately 5% of the videos are annotated with more than one class.\r\n\r\nSource: [Review of Action Recognition and Detection Methods](https://arxiv.org/abs/1610.06906)\r\n\r\nImage Source: [Computer Vision for Sports](https://www.researchgate.net/publication/316477606_Computer_vision_for_sports_Current_applications_and_research_topics)","description_withheld":null,"homepage":"https://cs.stanford.edu/people/karpathy/deepvideo/","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/large-scale-video-classification-with-1","title":"Large-Scale Video Classification with Convolutional Neural Networks","first_author":"Andrej Karpathy","url":null},"license":{"name":"CC BY 3.0","url":"https://cs.stanford.edu/people/karpathy/deepvideo/#:~:is%20licensed%20under"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Action Recognition In Videos","url":"/task/action-recognition-in-videos-2","datasets_with_task":"/datasets/task/action-recognition-in-videos-2"}],"languages":[],"variants":["Sports-1M"],"data_loaders":[],"num_papers_in_archive":164,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-recognition-in-videos-on-sports-1m","task":"Action Recognition","dataset_variant":"Sports-1M","rows":9,"metrics":["Video hit@1 ","Video hit@5","Clip Hit@1"],"first_row_in_archive_order":{"model":"ip-CSN-152 (RGB)","paper":"/paper/video-classification-with-channel-separated","metrics":{"Video hit@1 ":"75.5","Video hit@5":"92.8"},"code_links":[{"title":"open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2"},{"title":"facebookresearch/R2Plus1D","url":"https://github.com/facebookresearch/R2Plus1D"},{"title":"facebookresearch/VMZ","url":"https://github.com/facebookresearch/VMZ"},{"title":"BB-Repos/BBaction","url":"https://github.com/BB-Repos/BBaction"},{"title":"salinasJJ/BBaction","url":"https://github.com/salinasJJ/BBaction"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/r2plus1d"},{"title":"Mind23-2/MindCode-62","url":"https://github.com/Mind23-2/MindCode-62"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-sports-1m-1","task":"Action Recognition In Videos","dataset_variant":"Sports-1M","rows":2,"metrics":["Video hit@1","Video hit@5"],"first_row_in_archive_order":{"model":"G-Blend","paper":"/paper/what-makes-training-multi-modal-networks-hard","metrics":{"Video hit@1":"74.8","Video hit@5":"92.4"},"code_links":[{"title":"facebookresearch/R2Plus1D","url":"https://github.com/facebookresearch/R2Plus1D"},{"title":"facebookresearch/VMZ","url":"https://github.com/facebookresearch/VMZ"},{"title":"guide2157/ChulaXrayClassifier","url":"https://github.com/guide2157/ChulaXrayClassifier"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"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":1,"pages_in_order":1,"rows_per_page":100,"shown":8,"of":8,"counts":{"papers_with_a_benchmark_row":8,"with_a_code_link":8,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"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"},"items":[{"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":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+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/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":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+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/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":3,"code_links":24,"syntology":{"read_at":"2026-10-05T00:36:11+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/learning-spatio-temporal-representation-with","slug":"learning-spatio-temporal-representation-with","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","date":"2017-11-28","arxiv_id":"1711.10305","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/youtube-8m-a-large-scale-video-classification","slug":"youtube-8m-a-large-scale-video-classification","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","date":"2016-09-27","arxiv_id":"1609.08675","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/youtube-8m-a-large-scale-video-classification#ran","syntology_url":"https://syntology.ai/paper/1609.08675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.08675"}}}},{"paper":"/paper/beyond-short-snippets-deep-networks-for-video","slug":"beyond-short-snippets-deep-networks-for-video","title":"Beyond Short Snippets: Deep Networks for Video Classification","date":"2015-03-31","arxiv_id":"1503.08909","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/beyond-short-snippets-deep-networks-for-video#ran","syntology_url":"https://syntology.ai/paper/1503.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.08909"}}}},{"paper":"/paper/learning-spatiotemporal-features-with-3d","slug":"learning-spatiotemporal-features-with-3d","title":"Learning Spatiotemporal Features with 3D Convolutional Networks","date":"2014-12-02","arxiv_id":"1412.0767","rows_on_this_dataset":1,"code_links":29,"syntology":null},{"paper":"/paper/large-scale-video-classification-with-1","slug":"large-scale-video-classification-with-1","title":"Large-Scale Video Classification with Convolutional Neural Networks","date":"2014-06-23","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"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":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+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/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":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+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/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":3,"code_links":24,"syntology":{"read_at":"2026-10-05T00:36:11+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/learning-spatio-temporal-representation-with","slug":"learning-spatio-temporal-representation-with","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","date":"2017-11-28","arxiv_id":"1711.10305","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/youtube-8m-a-large-scale-video-classification","slug":"youtube-8m-a-large-scale-video-classification","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","date":"2016-09-27","arxiv_id":"1609.08675","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/youtube-8m-a-large-scale-video-classification#ran","syntology_url":"https://syntology.ai/paper/1609.08675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.08675"}}}},{"paper":"/paper/beyond-short-snippets-deep-networks-for-video","slug":"beyond-short-snippets-deep-networks-for-video","title":"Beyond Short Snippets: Deep Networks for Video Classification","date":"2015-03-31","arxiv_id":"1503.08909","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/beyond-short-snippets-deep-networks-for-video#ran","syntology_url":"https://syntology.ai/paper/1503.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.08909"}}}},{"paper":"/paper/learning-spatiotemporal-features-with-3d","slug":"learning-spatiotemporal-features-with-3d","title":"Learning Spatiotemporal Features with 3D Convolutional Networks","date":"2014-12-02","arxiv_id":"1412.0767","rows_on_this_dataset":1,"code_links":29,"syntology":null},{"paper":"/paper/large-scale-video-classification-with-1","slug":"large-scale-video-classification-with-1","title":"Large-Scale Video Classification with Convolutional Neural Networks","date":"2014-06-23","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/sports-1m/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/sports-1m/papers/ran/1","json":"/dataset/sports-1m/papers/ran/1.json","rows":5}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":5,"samples_harvested":32,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":4,"samples_unverified":13,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"1fe14c635ee7fb7fc7a369779629d43c7182ca7507e17dd3706f8ca72c218c07","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}