{"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/coin","name":"COIN","full_name":null,"description_markdown":"The **COIN** dataset (a large-scale dataset for COmprehensive INstructional video analysis) consists of 11,827 videos related to 180 different tasks in 12 domains (e.g., vehicles, gadgets, etc.) related to our daily life. The videos are all collected from YouTube. The average length of a video is 2.36 minutes. Each video is labelled with 3.91 step segments, where each segment lasts 14.91 seconds on average. In total, the dataset contains videos of 476 hours, with 46,354 annotated segments.\r\n\r\nSource: [COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis](/paper/coin-a-large-scale-dataset-for-comprehensive)","description_withheld":null,"homepage":"https://coin-dataset.github.io/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/coin-a-large-scale-dataset-for-comprehensive","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","first_author":"Yansong Tang","url":null},"license":{"name":"Custom","url":"https://coin-dataset.github.io/"},"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 Localization","url":"/task/action-localization","datasets_with_task":"/datasets/task/action-localization"},{"name":"Temporal Action Localization","url":"/task/action-recognition","datasets_with_task":"/datasets/task/action-recognition"},{"name":"Action Segmentation","url":"/task/action-segmentation","datasets_with_task":"/datasets/task/action-segmentation"},{"name":"Video Classification","url":"/task/video-classification","datasets_with_task":"/datasets/task/video-classification"}],"languages":[],"variants":["COIN"],"data_loaders":[],"num_papers_in_archive":105,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-segmentation-on-coin","task":"Action Segmentation","dataset_variant":"COIN","rows":9,"metrics":["Frame accuracy"],"first_row_in_archive_order":{"model":"UnLoc-L","paper":"/paper/unloc-a-unified-framework-for-video","metrics":{"Frame accuracy":"72.8"},"code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-classification-on-coin-1","task":"Video Classification","dataset_variant":"COIN","rows":7,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"HERMES","paper":"/paper/bridging-episodes-and-semantics-a-novel","metrics":{"Accuracy (%)":"93.5"},"code_links":[{"title":"joslefaure/HERMES","url":"https://github.com/joslefaure/HERMES"}]},"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":15,"of":15,"counts":{"papers_with_a_benchmark_row":15,"with_a_code_link":13,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":15,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/bridging-episodes-and-semantics-a-novel","slug":"bridging-episodes-and-semantics-a-novel","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","date":"2024-08-30","arxiv_id":"2408.17443","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":6,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["joslefaure/HERMES"],"state":"official (archive's flag): 7 ran","n_ran":7,"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/bridging-episodes-and-semantics-a-novel#ran","syntology_url":"https://syntology.ai/paper/2408.17443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17443"}}}},{"paper":"/paper/ma-lmm-memory-augmented-large-multimodal","slug":"ma-lmm-memory-augmented-large-multimodal","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","date":"2024-04-08","arxiv_id":"2404.05726","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["boheumd/MA-LMM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"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/ma-lmm-memory-augmented-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.05726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05726"}}}},{"paper":"/paper/multi-granularity-correspondence-learning-1","slug":"multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","arxiv_id":"2401.16702","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"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/multi-granularity-correspondence-learning-1#ran","syntology_url":"https://syntology.ai/paper/2401.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16702"}}}},{"paper":"/paper/unloc-a-unified-framework-for-video","slug":"unloc-a-unified-framework-for-video","title":"UnLoc: A Unified Framework for Video Localization Tasks","date":"2023-08-21","arxiv_id":"2308.11062","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/selective-structured-state-spaces-for-long","slug":"selective-structured-state-spaces-for-long","title":"Selective Structured State-Spaces for Long-Form Video Understanding","date":"2023-03-25","arxiv_id":"2303.14526","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-movie-scene-detection-using-state","slug":"efficient-movie-scene-detection-using-state","title":"Efficient Movie Scene Detection using State-Space Transformers","date":"2022-12-29","arxiv_id":"2212.14427","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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":["md-mohaiminul/trans4mer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-movie-scene-detection-using-state#ran","syntology_url":"https://syntology.ai/paper/2212.14427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14427"}}}},{"paper":"/paper/long-movie-clip-classification-with-state","slug":"long-movie-clip-classification-with-state","title":"Long Movie Clip Classification with State-Space Video Models","date":"2022-04-04","arxiv_id":"2204.01692","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":11,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":8,"samples_unverified":7,"pointer_only_for_licence":2,"official":{"repos":["md-mohaiminul/ViS4mer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/long-movie-clip-classification-with-state#ran","syntology_url":"https://syntology.ai/paper/2204.01692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01692"}}}},{"paper":"/paper/learning-to-recognize-procedural-activities","slug":"learning-to-recognize-procedural-activities","title":"Learning To Recognize Procedural Activities with Distant Supervision","date":"2022-01-26","arxiv_id":"2201.10990","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videoclip-contrastive-pre-training-for-zero","slug":"videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","date":"2021-09-28","arxiv_id":"2109.14084","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/taco-token-aware-cascade-contrastive-learning","slug":"taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","date":"2021-08-23","arxiv_id":"2108.09980","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vlm-task-agnostic-video-language-model-pre","slug":"vlm-task-agnostic-video-language-model-pre","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","date":"2021-05-20","arxiv_id":"2105.09996","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/actbert-learning-global-local-video-text-1","slug":"actbert-learning-global-local-video-text-1","title":"ActBERT: Learning Global-Local Video-Text Representations","date":"2020-11-14","arxiv_id":"2011.07231","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","rows_on_this_dataset":1,"code_links":2,"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":1,"official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/univilm-a-unified-video-and-language-pre#ran","syntology_url":"https://syntology.ai/paper/2002.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06353"}}}},{"paper":"/paper/end-to-end-learning-of-visual-representations","slug":"end-to-end-learning-of-visual-representations","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","date":"2019-12-13","arxiv_id":"1912.06430","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["antoine77340/MIL-NCE_HowTo100M"],"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/end-to-end-learning-of-visual-representations#ran","syntology_url":"https://syntology.ai/paper/1912.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06430"}}}},{"paper":"/paper/temporal-segment-networks-for-action","slug":"temporal-segment-networks-for-action","title":"Temporal Segment Networks for Action Recognition in Videos","date":"2017-05-08","arxiv_id":"1705.02953","rows_on_this_dataset":1,"code_links":11,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/bridging-episodes-and-semantics-a-novel","slug":"bridging-episodes-and-semantics-a-novel","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","date":"2024-08-30","arxiv_id":"2408.17443","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":6,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["joslefaure/HERMES"],"state":"official (archive's flag): 7 ran","n_ran":7,"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/bridging-episodes-and-semantics-a-novel#ran","syntology_url":"https://syntology.ai/paper/2408.17443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17443"}}}},{"paper":"/paper/ma-lmm-memory-augmented-large-multimodal","slug":"ma-lmm-memory-augmented-large-multimodal","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","date":"2024-04-08","arxiv_id":"2404.05726","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["boheumd/MA-LMM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"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/ma-lmm-memory-augmented-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.05726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05726"}}}},{"paper":"/paper/multi-granularity-correspondence-learning-1","slug":"multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","arxiv_id":"2401.16702","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"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/multi-granularity-correspondence-learning-1#ran","syntology_url":"https://syntology.ai/paper/2401.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16702"}}}},{"paper":"/paper/unloc-a-unified-framework-for-video","slug":"unloc-a-unified-framework-for-video","title":"UnLoc: A Unified Framework for Video Localization Tasks","date":"2023-08-21","arxiv_id":"2308.11062","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/selective-structured-state-spaces-for-long","slug":"selective-structured-state-spaces-for-long","title":"Selective Structured State-Spaces for Long-Form Video Understanding","date":"2023-03-25","arxiv_id":"2303.14526","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-movie-scene-detection-using-state","slug":"efficient-movie-scene-detection-using-state","title":"Efficient Movie Scene Detection using State-Space Transformers","date":"2022-12-29","arxiv_id":"2212.14427","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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":["md-mohaiminul/trans4mer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-movie-scene-detection-using-state#ran","syntology_url":"https://syntology.ai/paper/2212.14427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14427"}}}},{"paper":"/paper/long-movie-clip-classification-with-state","slug":"long-movie-clip-classification-with-state","title":"Long Movie Clip Classification with State-Space Video Models","date":"2022-04-04","arxiv_id":"2204.01692","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":11,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":8,"samples_unverified":7,"pointer_only_for_licence":2,"official":{"repos":["md-mohaiminul/ViS4mer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/long-movie-clip-classification-with-state#ran","syntology_url":"https://syntology.ai/paper/2204.01692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01692"}}}},{"paper":"/paper/learning-to-recognize-procedural-activities","slug":"learning-to-recognize-procedural-activities","title":"Learning To Recognize Procedural Activities with Distant Supervision","date":"2022-01-26","arxiv_id":"2201.10990","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videoclip-contrastive-pre-training-for-zero","slug":"videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","date":"2021-09-28","arxiv_id":"2109.14084","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/taco-token-aware-cascade-contrastive-learning","slug":"taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","date":"2021-08-23","arxiv_id":"2108.09980","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vlm-task-agnostic-video-language-model-pre","slug":"vlm-task-agnostic-video-language-model-pre","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","date":"2021-05-20","arxiv_id":"2105.09996","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/actbert-learning-global-local-video-text-1","slug":"actbert-learning-global-local-video-text-1","title":"ActBERT: Learning Global-Local Video-Text Representations","date":"2020-11-14","arxiv_id":"2011.07231","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","rows_on_this_dataset":1,"code_links":2,"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":1,"official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/univilm-a-unified-video-and-language-pre#ran","syntology_url":"https://syntology.ai/paper/2002.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06353"}}}},{"paper":"/paper/end-to-end-learning-of-visual-representations","slug":"end-to-end-learning-of-visual-representations","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","date":"2019-12-13","arxiv_id":"1912.06430","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["antoine77340/MIL-NCE_HowTo100M"],"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/end-to-end-learning-of-visual-representations#ran","syntology_url":"https://syntology.ai/paper/1912.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06430"}}}},{"paper":"/paper/temporal-segment-networks-for-action","slug":"temporal-segment-networks-for-action","title":"Temporal Segment Networks for Action Recognition in Videos","date":"2017-05-08","arxiv_id":"1705.02953","rows_on_this_dataset":1,"code_links":11,"syntology":null}],"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/dataset/coin/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/coin/papers/ran/1","json":"/dataset/coin/papers/ran/1.json","rows":7}],"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":7,"samples_harvested":51,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":10,"samples_ran_instrument_failed":25,"samples_unverified":16,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":7,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":3,"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":"53118de77f9c7d2b53ac8d30d7f759a4a7d95cb0aa0c06a994681b492c12a62d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}