{"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/breakfast","name":"Breakfast","full_name":"The Breakfast Actions Dataset","description_markdown":"The **Breakfast** Actions Dataset comprises of 10 actions related to breakfast preparation, performed by 52 different individuals in 18 different kitchens. The dataset is one of the largest fully annotated datasets available. The actions are recorded “in the wild” as opposed to a single controlled lab environment. It consists of over 77 hours of video recordings.\r\n\r\nSource: [https://serre-lab.clps.brown.edu/resource/breakfast-actions-dataset/](https://serre-lab.clps.brown.edu/resource/breakfast-actions-dataset/)\r\nImage Source: [https://serre-lab.clps.brown.edu/resource/breakfast-actions-dataset/](https://serre-lab.clps.brown.edu/resource/breakfast-actions-dataset/)","description_withheld":null,"homepage":"https://serre-lab.clps.brown.edu/resource/breakfast-actions-dataset/","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-language-of-actions-recovering-the-syntax","title":"The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities","first_author":"Hilde Kuehne","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Actions","url":"/datasets/modality/actions"}],"tasks":[{"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"},{"name":"Unsupervised Action Segmentation","url":"/task/unsupervised-action-segmentation","datasets_with_task":"/datasets/task/unsupervised-action-segmentation"},{"name":"Weakly Supervised Action Segmentation (Transcript)","url":"/task/weakly-supervised-action-segmentation","datasets_with_task":"/datasets/task/weakly-supervised-action-segmentation"},{"name":"Weakly Supervised Action Segmentation (Action Set))","url":"/task/weakly-supervised-action-segmentation-action","datasets_with_task":"/datasets/task/weakly-supervised-action-segmentation-action"},{"name":"Long-video Activity Recognition","url":"/task/long-video-activity-recognition","datasets_with_task":"/datasets/task/long-video-activity-recognition"}],"languages":[],"variants":["Breakfast"],"data_loaders":[],"num_papers_in_archive":179,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset_variant":"Breakfast","rows":37,"metrics":["Average F1","F1@50%","F1@25%","F1@10%","Edit","Acc","mIoU","F1"],"first_row_in_archive_order":{"model":"AdaFocus (newly extracted I3D-features, LT-Context model)","paper":"/paper/adafocus-towards-end-to-end-weakly-supervised","metrics":{"Acc":"78.0","Average F1":"76.2","Edit":"78.3","F1@10%":"82.1","F1@25%":"79.0","F1@50%":"67.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-classification-on-breakfast","task":"Video Classification","dataset_variant":"Breakfast","rows":9,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"HERMES","paper":"/paper/bridging-episodes-and-semantics-a-novel","metrics":{"Accuracy (%)":"95.2"},"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"},{"leaderboard":"/sota/long-video-activity-recognition-on-breakfast","task":"Long-video Activity Recognition","dataset_variant":"Breakfast","rows":8,"metrics":["mAP"],"first_row_in_archive_order":{"model":"AdaFocus (MViT-Breakfast-Pretrain-feature, GHRM)","paper":"/paper/adafocus-towards-end-to-end-weakly-supervised","metrics":{"mAP":"79.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-action-segmentation-on-breakfast","task":"Unsupervised Action Segmentation","dataset_variant":"Breakfast","rows":8,"metrics":["F1","Acc","JSD","Precision","Recall","mIoU"],"first_row_in_archive_order":{"model":"HVQ","paper":"/paper/hierarchical-vector-quantization-for","metrics":{"Acc":"54.4","F1":"39.7","JSD":"82.5","Precision":"35.6","Recall":"44.9"},"code_links":[{"title":"fedespu/hvq","url":"https://github.com/fedespu/hvq"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-action-segmentation","task":"Weakly Supervised Action Segmentation (Transcript)","dataset_variant":"Breakfast","rows":7,"metrics":["Acc"],"first_row_in_archive_order":{"model":"AUL","paper":"/paper/is-weakly-supervised-action-segmentation","metrics":{"Acc":"67.3"},"code_links":[{"title":"fandulu/DD-Net","url":"https://github.com/fandulu/DD-Net"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-action-segmentation-action","task":"Weakly Supervised Action Segmentation (Action Set))","dataset_variant":"Breakfast","rows":2,"metrics":["Acc"],"first_row_in_archive_order":{"model":"AdaFocus (newly extracted I3D-features, POC model)","paper":"/paper/adafocus-towards-end-to-end-weakly-supervised","metrics":{"Acc":"49.6"},"code_links":[]},"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":56,"of":56,"counts":{"papers_with_a_benchmark_row":56,"with_a_code_link":39,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":56,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":12,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":12,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/hierarchical-vector-quantization-for","slug":"hierarchical-vector-quantization-for","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","date":"2024-12-23","arxiv_id":"2412.17640","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/asquery-a-query-based-model-for-action","slug":"asquery-a-query-based-model-for-action","title":"ASQuery: A Query-based Model for Action Segmentation","date":"2024-09-30","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/efficient-temporal-action-segmentation-via","slug":"efficient-temporal-action-segmentation-via","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","date":"2024-05-25","arxiv_id":"2405.15995","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/temporally-consistent-unbalanced-optimal","slug":"temporally-consistent-unbalanced-optimal","title":"Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation","date":"2024-04-01","arxiv_id":"2404.01518","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fact-frame-action-cross-attention-temporal","slug":"fact-frame-action-cross-attention-temporal","title":"FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adafocus-towards-end-to-end-weakly-supervised","slug":"adafocus-towards-end-to-end-weakly-supervised","title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","date":"2023-11-28","arxiv_id":"2311.17118","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/is-weakly-supervised-action-segmentation","slug":"is-weakly-supervised-action-segmentation","title":"Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning","date":"2023-10-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bit-bi-level-temporal-modeling-for-efficient","slug":"bit-bi-level-temporal-modeling-for-efficient","title":"BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation","date":"2023-08-28","arxiv_id":"2308.14900","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/how-much-temporal-long-term-context-is-needed","slug":"how-much-temporal-long-term-context-is-needed","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","date":"2023-08-22","arxiv_id":"2308.11358","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["ltcontext/ltcontext"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/how-much-temporal-long-term-context-is-needed#ran","syntology_url":"https://syntology.ai/paper/2308.11358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11358"}}}},{"paper":"/paper/sf-tmn-slowfast-temporal-modeling-network-for","slug":"sf-tmn-slowfast-temporal-modeling-network-for","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","date":"2023-06-15","arxiv_id":"2306.08859","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/permutation-aware-action-segmentation-via","slug":"permutation-aware-action-segmentation-via","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","date":"2023-05-31","arxiv_id":"2305.19478","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/leveraging-triplet-loss-for-unsupervised","slug":"leveraging-triplet-loss-for-unsupervised","title":"Leveraging triplet loss for unsupervised action segmentation","date":"2023-04-13","arxiv_id":"2304.06403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/diffusion-action-segmentation","slug":"diffusion-action-segmentation","title":"Diffusion Action Segmentation","date":"2023-03-31","arxiv_id":"2303.17959","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusion-action-segmentation#ran","syntology_url":"https://syntology.ai/paper/2303.17959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17959"}}}},{"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/aspnet-action-segmentation-with-shared","slug":"aspnet-action-segmentation-with-shared","title":"ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources","date":"2023-01-01","arxiv_id":null,"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/unified-fully-and-timestamp-supervised","slug":"unified-fully-and-timestamp-supervised","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","date":"2022-09-01","arxiv_id":"2209.00638","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["boschresearch/uvast"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-fully-and-timestamp-supervised#ran","syntology_url":"https://syntology.ai/paper/2209.00638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.00638"}}}},{"paper":"/paper/rf-next-efficient-receptive-field-search-for","slug":"rf-next-efficient-receptive-field-search-for","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","date":"2022-06-14","arxiv_id":"2206.06637","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["ShangHua-Gao/RFNext"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rf-next-efficient-receptive-field-search-for#ran","syntology_url":"https://syntology.ai/paper/2206.06637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06637"}}}},{"paper":"/paper/efficient-u-transformer-with-boundary-aware","slug":"efficient-u-transformer-with-boundary-aware","title":"Do we really need temporal convolutions in action segmentation?","date":"2022-05-26","arxiv_id":"2205.13425","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cross-enhancement-transformer-for-action","slug":"cross-enhancement-transformer-for-action","title":"Cross-Enhancement Transformer for Action Segmentation","date":"2022-05-19","arxiv_id":"2205.09445","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/maximization-and-restoration-action","slug":"maximization-and-restoration-action","title":"Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction","date":"2022-05-02","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/set-supervised-action-learning-in-procedural","slug":"set-supervised-action-learning-in-procedural","title":"Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency","date":"2022-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/asformer-transformer-for-action-segmentation","slug":"asformer-transformer-for-action-segmentation","title":"ASFormer: Transformer for Action Segmentation","date":"2021-10-16","arxiv_id":"2110.08568","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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":0,"official":{"repos":["chinayi/asformer"],"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/asformer-transformer-for-action-segmentation#ran","syntology_url":"https://syntology.ai/paper/2110.08568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08568"}}}},{"paper":"/paper/fifa-fast-inference-approximation-for-action","slug":"fifa-fast-inference-approximation-for-action","title":"FIFA: Fast Inference Approximation for Action Segmentation","date":"2021-08-09","arxiv_id":"2108.03894","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/graph-based-high-order-relation-modeling-for","slug":"graph-based-high-order-relation-modeling-for","title":"Graph-Based High-Order Relation Modeling for Long-Term Action Recognition","date":"2021-06-19","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-activity-segmentation-by-joint","slug":"unsupervised-activity-segmentation-by-joint","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","date":"2021-05-27","arxiv_id":"2105.13353","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["trquhuytin/TOT-CVPR22"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-activity-segmentation-by-joint#ran","syntology_url":"https://syntology.ai/paper/2105.13353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13353"}}}},{"paper":"/paper/coarse-to-fine-multi-resolution-temporal","slug":"coarse-to-fine-multi-resolution-temporal","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","date":"2021-05-23","arxiv_id":"2105.10859","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-two-step-networks-for-temporal","slug":"efficient-two-step-networks-for-temporal","title":"Efficient Two-Step Networks for Temporal Action Segmentation","date":"2021-04-30","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-discriminative-embedding-for-sub","slug":"unsupervised-discriminative-embedding-for-sub","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","date":"2021-04-30","arxiv_id":"2105.00067","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-segmentation-with-mixed-temporal","slug":"action-segmentation-with-mixed-temporal","title":"Action Segmentation with Mixed Temporal Domain Adaptation","date":"2021-04-15","arxiv_id":"2104.07461","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-shuffle-alternating-learning-for","slug":"action-shuffle-alternating-learning-for","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","date":"2021-04-05","arxiv_id":"2104.02116","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporally-weighted-hierarchical-clustering","slug":"temporally-weighted-hierarchical-clustering","title":"Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation","date":"2021-03-20","arxiv_id":"2103.11264","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["ssarfraz/FINCH-CLustering"],"state":"official (archive's flag): 5 ran","n_ran":5,"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/temporally-weighted-hierarchical-clustering#ran","syntology_url":"https://syntology.ai/paper/2103.11264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11264"}}}},{"paper":"/paper/depthwise-separable-temporal-convolutional","slug":"depthwise-separable-temporal-convolutional","title":"Depthwise Separable Temporal Convolutional Network for Action Segmentation","date":"2021-01-19","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/global2local-efficient-structure-search-for","slug":"global2local-efficient-structure-search-for","title":"Global2Local: Efficient Structure Search for Video Action Segmentation","date":"2021-01-04","arxiv_id":"2101.00910","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+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":["ShangHua-Gao/G2L-search"],"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/global2local-efficient-structure-search-for#ran","syntology_url":"https://syntology.ai/paper/2101.00910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00910"}}}},{"paper":"/paper/refining-action-segmentation-with","slug":"refining-action-segmentation-with","title":"Refining Action Segmentation With Hierarchical Video Representations","date":"2021-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-action-segmentation-and","slug":"weakly-supervised-action-segmentation-and","title":"Weakly-Supervised Action Segmentation and Alignment via Transcript-Aware Union-of-Subspaces Learning","date":"2021-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-relational-modeling-with-self","slug":"temporal-relational-modeling-with-self","title":"Temporal Relational Modeling with Self-Supervision for Action Segmentation","date":"2020-12-14","arxiv_id":"2012.07508","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boundary-aware-cascade-networks-for-temporal","slug":"boundary-aware-cascade-networks-for-temporal","title":"Boundary-Aware Cascade Networks for Temporal Action Segmentation","date":"2020-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/alleviating-over-segmentation-errors-by","slug":"alleviating-over-segmentation-errors-by","title":"Alleviating Over-segmentation Errors by Detecting Action Boundaries","date":"2020-07-14","arxiv_id":"2007.06866","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yiskw713/asrf"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/alleviating-over-segmentation-errors-by#ran","syntology_url":"https://syntology.ai/paper/2007.06866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06866"}}}},{"paper":"/paper/ms-tcn-multi-stage-temporal-convolutional-2","slug":"ms-tcn-multi-stage-temporal-convolutional-2","title":"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation","date":"2020-06-16","arxiv_id":"2006.09220","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/improving-action-segmentation-via-graph-based","slug":"improving-action-segmentation-via-graph-based","title":"Improving Action Segmentation via Graph-Based Temporal Reasoning","date":"2020-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-segmentation-with-joint-self","slug":"action-segmentation-with-joint-self","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","date":"2020-03-05","arxiv_id":"2003.02824","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":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["cmhungsteve/SSTDA"],"state":"official (archive's flag): 3 ran","n_ran":3,"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/action-segmentation-with-joint-self#ran","syntology_url":"https://syntology.ai/paper/2003.02824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02824"}}}},{"paper":"/paper/weakly-supervised-energy-based-learning-for","slug":"weakly-supervised-energy-based-learning-for","title":"Weakly Supervised Energy-Based Learning for Action Segmentation","date":"2019-09-28","arxiv_id":"1909.13155","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videograph-recognizing-minutes-long-human","slug":"videograph-recognizing-minutes-long-human","title":"VideoGraph: Recognizing Minutes-Long Human Activities in Videos","date":"2019-05-13","arxiv_id":"1905.05143","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-learning-of-action-classes-with","slug":"unsupervised-learning-of-action-classes-with","title":"Unsupervised learning of action classes with continuous temporal embedding","date":"2019-04-08","arxiv_id":"1904.04189","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/weakly-supervised-action-segmentation-using","slug":"weakly-supervised-action-segmentation-using","title":"Fast Weakly Supervised Action Segmentation Using Mutual Consistency","date":"2019-04-05","arxiv_id":"1904.03116","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ms-tcn-multi-stage-temporal-convolutional","slug":"ms-tcn-multi-stage-temporal-convolutional","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","date":"2019-03-05","arxiv_id":"1903.01945","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/d3tw-discriminative-differentiable-dynamic","slug":"d3tw-discriminative-differentiable-dynamic","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","date":"2019-01-09","arxiv_id":"1901.02598","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/timeception-for-complex-action-recognition","slug":"timeception-for-complex-action-recognition","title":"Timeception for Complex Action Recognition","date":"2018-12-04","arxiv_id":"1812.01289","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/a-perceptual-prediction-framework-for-self","slug":"a-perceptual-prediction-framework-for-self","title":"A Perceptual Prediction Framework for Self Supervised Event Segmentation","date":"2018-11-12","arxiv_id":"1811.04869","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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":["CVPRUSFTampa/EventSegmentation"],"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/a-perceptual-prediction-framework-for-self#ran","syntology_url":"https://syntology.ai/paper/1811.04869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04869"}}}},{"paper":"/paper/neuralnetwork-viterbi-a-framework-for-weakly","slug":"neuralnetwork-viterbi-a-framework-for-weakly","title":"NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning","date":"2018-05-17","arxiv_id":"1805.06875","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/actionvlad-learning-spatio-temporal","slug":"actionvlad-learning-spatio-temporal","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","date":"2017-04-10","arxiv_id":"1704.02895","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/hierarchical-vector-quantization-for","slug":"hierarchical-vector-quantization-for","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","date":"2024-12-23","arxiv_id":"2412.17640","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/asquery-a-query-based-model-for-action","slug":"asquery-a-query-based-model-for-action","title":"ASQuery: A Query-based Model for Action Segmentation","date":"2024-09-30","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/efficient-temporal-action-segmentation-via","slug":"efficient-temporal-action-segmentation-via","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","date":"2024-05-25","arxiv_id":"2405.15995","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/temporally-consistent-unbalanced-optimal","slug":"temporally-consistent-unbalanced-optimal","title":"Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation","date":"2024-04-01","arxiv_id":"2404.01518","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fact-frame-action-cross-attention-temporal","slug":"fact-frame-action-cross-attention-temporal","title":"FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adafocus-towards-end-to-end-weakly-supervised","slug":"adafocus-towards-end-to-end-weakly-supervised","title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","date":"2023-11-28","arxiv_id":"2311.17118","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/is-weakly-supervised-action-segmentation","slug":"is-weakly-supervised-action-segmentation","title":"Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning","date":"2023-10-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bit-bi-level-temporal-modeling-for-efficient","slug":"bit-bi-level-temporal-modeling-for-efficient","title":"BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation","date":"2023-08-28","arxiv_id":"2308.14900","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/how-much-temporal-long-term-context-is-needed","slug":"how-much-temporal-long-term-context-is-needed","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","date":"2023-08-22","arxiv_id":"2308.11358","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["ltcontext/ltcontext"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/how-much-temporal-long-term-context-is-needed#ran","syntology_url":"https://syntology.ai/paper/2308.11358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11358"}}}},{"paper":"/paper/sf-tmn-slowfast-temporal-modeling-network-for","slug":"sf-tmn-slowfast-temporal-modeling-network-for","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","date":"2023-06-15","arxiv_id":"2306.08859","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/permutation-aware-action-segmentation-via","slug":"permutation-aware-action-segmentation-via","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","date":"2023-05-31","arxiv_id":"2305.19478","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/leveraging-triplet-loss-for-unsupervised","slug":"leveraging-triplet-loss-for-unsupervised","title":"Leveraging triplet loss for unsupervised action segmentation","date":"2023-04-13","arxiv_id":"2304.06403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/diffusion-action-segmentation","slug":"diffusion-action-segmentation","title":"Diffusion Action Segmentation","date":"2023-03-31","arxiv_id":"2303.17959","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusion-action-segmentation#ran","syntology_url":"https://syntology.ai/paper/2303.17959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17959"}}}},{"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/aspnet-action-segmentation-with-shared","slug":"aspnet-action-segmentation-with-shared","title":"ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources","date":"2023-01-01","arxiv_id":null,"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/unified-fully-and-timestamp-supervised","slug":"unified-fully-and-timestamp-supervised","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","date":"2022-09-01","arxiv_id":"2209.00638","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["boschresearch/uvast"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-fully-and-timestamp-supervised#ran","syntology_url":"https://syntology.ai/paper/2209.00638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.00638"}}}},{"paper":"/paper/rf-next-efficient-receptive-field-search-for","slug":"rf-next-efficient-receptive-field-search-for","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","date":"2022-06-14","arxiv_id":"2206.06637","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["ShangHua-Gao/RFNext"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rf-next-efficient-receptive-field-search-for#ran","syntology_url":"https://syntology.ai/paper/2206.06637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06637"}}}},{"paper":"/paper/efficient-u-transformer-with-boundary-aware","slug":"efficient-u-transformer-with-boundary-aware","title":"Do we really need temporal convolutions in action segmentation?","date":"2022-05-26","arxiv_id":"2205.13425","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cross-enhancement-transformer-for-action","slug":"cross-enhancement-transformer-for-action","title":"Cross-Enhancement Transformer for Action Segmentation","date":"2022-05-19","arxiv_id":"2205.09445","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/maximization-and-restoration-action","slug":"maximization-and-restoration-action","title":"Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction","date":"2022-05-02","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/set-supervised-action-learning-in-procedural","slug":"set-supervised-action-learning-in-procedural","title":"Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency","date":"2022-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/asformer-transformer-for-action-segmentation","slug":"asformer-transformer-for-action-segmentation","title":"ASFormer: Transformer for Action Segmentation","date":"2021-10-16","arxiv_id":"2110.08568","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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":0,"official":{"repos":["chinayi/asformer"],"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/asformer-transformer-for-action-segmentation#ran","syntology_url":"https://syntology.ai/paper/2110.08568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08568"}}}},{"paper":"/paper/fifa-fast-inference-approximation-for-action","slug":"fifa-fast-inference-approximation-for-action","title":"FIFA: Fast Inference Approximation for Action Segmentation","date":"2021-08-09","arxiv_id":"2108.03894","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/graph-based-high-order-relation-modeling-for","slug":"graph-based-high-order-relation-modeling-for","title":"Graph-Based High-Order Relation Modeling for Long-Term Action Recognition","date":"2021-06-19","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-activity-segmentation-by-joint","slug":"unsupervised-activity-segmentation-by-joint","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","date":"2021-05-27","arxiv_id":"2105.13353","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["trquhuytin/TOT-CVPR22"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-activity-segmentation-by-joint#ran","syntology_url":"https://syntology.ai/paper/2105.13353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13353"}}}},{"paper":"/paper/coarse-to-fine-multi-resolution-temporal","slug":"coarse-to-fine-multi-resolution-temporal","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","date":"2021-05-23","arxiv_id":"2105.10859","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-two-step-networks-for-temporal","slug":"efficient-two-step-networks-for-temporal","title":"Efficient Two-Step Networks for Temporal Action Segmentation","date":"2021-04-30","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-discriminative-embedding-for-sub","slug":"unsupervised-discriminative-embedding-for-sub","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","date":"2021-04-30","arxiv_id":"2105.00067","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-segmentation-with-mixed-temporal","slug":"action-segmentation-with-mixed-temporal","title":"Action Segmentation with Mixed Temporal Domain Adaptation","date":"2021-04-15","arxiv_id":"2104.07461","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-shuffle-alternating-learning-for","slug":"action-shuffle-alternating-learning-for","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","date":"2021-04-05","arxiv_id":"2104.02116","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporally-weighted-hierarchical-clustering","slug":"temporally-weighted-hierarchical-clustering","title":"Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation","date":"2021-03-20","arxiv_id":"2103.11264","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["ssarfraz/FINCH-CLustering"],"state":"official (archive's flag): 5 ran","n_ran":5,"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/temporally-weighted-hierarchical-clustering#ran","syntology_url":"https://syntology.ai/paper/2103.11264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11264"}}}},{"paper":"/paper/depthwise-separable-temporal-convolutional","slug":"depthwise-separable-temporal-convolutional","title":"Depthwise Separable Temporal Convolutional Network for Action Segmentation","date":"2021-01-19","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/global2local-efficient-structure-search-for","slug":"global2local-efficient-structure-search-for","title":"Global2Local: Efficient Structure Search for Video Action Segmentation","date":"2021-01-04","arxiv_id":"2101.00910","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+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":["ShangHua-Gao/G2L-search"],"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/global2local-efficient-structure-search-for#ran","syntology_url":"https://syntology.ai/paper/2101.00910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00910"}}}},{"paper":"/paper/refining-action-segmentation-with","slug":"refining-action-segmentation-with","title":"Refining Action Segmentation With Hierarchical Video Representations","date":"2021-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-action-segmentation-and","slug":"weakly-supervised-action-segmentation-and","title":"Weakly-Supervised Action Segmentation and Alignment via Transcript-Aware Union-of-Subspaces Learning","date":"2021-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-relational-modeling-with-self","slug":"temporal-relational-modeling-with-self","title":"Temporal Relational Modeling with Self-Supervision for Action Segmentation","date":"2020-12-14","arxiv_id":"2012.07508","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boundary-aware-cascade-networks-for-temporal","slug":"boundary-aware-cascade-networks-for-temporal","title":"Boundary-Aware Cascade Networks for Temporal Action Segmentation","date":"2020-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/alleviating-over-segmentation-errors-by","slug":"alleviating-over-segmentation-errors-by","title":"Alleviating Over-segmentation Errors by Detecting Action Boundaries","date":"2020-07-14","arxiv_id":"2007.06866","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yiskw713/asrf"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/alleviating-over-segmentation-errors-by#ran","syntology_url":"https://syntology.ai/paper/2007.06866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06866"}}}},{"paper":"/paper/ms-tcn-multi-stage-temporal-convolutional-2","slug":"ms-tcn-multi-stage-temporal-convolutional-2","title":"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation","date":"2020-06-16","arxiv_id":"2006.09220","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/improving-action-segmentation-via-graph-based","slug":"improving-action-segmentation-via-graph-based","title":"Improving Action Segmentation via Graph-Based Temporal Reasoning","date":"2020-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/action-segmentation-with-joint-self","slug":"action-segmentation-with-joint-self","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","date":"2020-03-05","arxiv_id":"2003.02824","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":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["cmhungsteve/SSTDA"],"state":"official (archive's flag): 3 ran","n_ran":3,"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/action-segmentation-with-joint-self#ran","syntology_url":"https://syntology.ai/paper/2003.02824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02824"}}}},{"paper":"/paper/weakly-supervised-energy-based-learning-for","slug":"weakly-supervised-energy-based-learning-for","title":"Weakly Supervised Energy-Based Learning for Action Segmentation","date":"2019-09-28","arxiv_id":"1909.13155","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/videograph-recognizing-minutes-long-human","slug":"videograph-recognizing-minutes-long-human","title":"VideoGraph: Recognizing Minutes-Long Human Activities in Videos","date":"2019-05-13","arxiv_id":"1905.05143","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-learning-of-action-classes-with","slug":"unsupervised-learning-of-action-classes-with","title":"Unsupervised learning of action classes with continuous temporal embedding","date":"2019-04-08","arxiv_id":"1904.04189","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/weakly-supervised-action-segmentation-using","slug":"weakly-supervised-action-segmentation-using","title":"Fast Weakly Supervised Action Segmentation Using Mutual Consistency","date":"2019-04-05","arxiv_id":"1904.03116","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ms-tcn-multi-stage-temporal-convolutional","slug":"ms-tcn-multi-stage-temporal-convolutional","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","date":"2019-03-05","arxiv_id":"1903.01945","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/d3tw-discriminative-differentiable-dynamic","slug":"d3tw-discriminative-differentiable-dynamic","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","date":"2019-01-09","arxiv_id":"1901.02598","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/timeception-for-complex-action-recognition","slug":"timeception-for-complex-action-recognition","title":"Timeception for Complex Action Recognition","date":"2018-12-04","arxiv_id":"1812.01289","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/a-perceptual-prediction-framework-for-self","slug":"a-perceptual-prediction-framework-for-self","title":"A Perceptual Prediction Framework for Self Supervised Event Segmentation","date":"2018-11-12","arxiv_id":"1811.04869","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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":["CVPRUSFTampa/EventSegmentation"],"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/a-perceptual-prediction-framework-for-self#ran","syntology_url":"https://syntology.ai/paper/1811.04869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04869"}}}},{"paper":"/paper/neuralnetwork-viterbi-a-framework-for-weakly","slug":"neuralnetwork-viterbi-a-framework-for-weakly","title":"NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning","date":"2018-05-17","arxiv_id":"1805.06875","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/actionvlad-learning-spatio-temporal","slug":"actionvlad-learning-spatio-temporal","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","date":"2017-04-10","arxiv_id":"1704.02895","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":14,"papers_where_code_ran_first_page":"/dataset/breakfast/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/breakfast/papers/ran/1","json":"/dataset/breakfast/papers/ran/1.json","rows":14}],"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":15,"samples_harvested":87,"samples_ran":67,"samples_constructed":6,"samples_ran_checked":38,"samples_ran_instrument_failed":29,"samples_unverified":20,"pointer_only_for_licence":19,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":14,"papers_with_a_run_with_no_instrument_failure":12,"papers_where_every_run_was_an_instrument_failure":2,"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":"1def71518b90f61e9f0a6ada966add6386697c5a56a927d97fb95c678f9206ca","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}