{"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":"/task/action-segmentation","name":"Action Segmentation","slug":"action-segmentation","description_markdown":"**Action Segmentation** is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.\n\n\n<span class=\"description-source\">Source: [TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation ](https://arxiv.org/abs/1705.07818)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":219,"papers_with_code":99,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":18,"subtasks":4,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/action-segmentation-on-breakfast-1","slug":"action-segmentation-on-breakfast-1","dataset":"Breakfast","dataset_url":"/dataset/breakfast","rows_in_archive":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_title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","paper_url":"/paper/adafocus-towards-end-to-end-weakly-supervised","paper_date":"2023-11-28","arxiv_id":"2311.17118","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-50-salads-1","slug":"action-segmentation-on-50-salads-1","dataset":"50 Salads","dataset_url":"/dataset/50-salads","rows_in_archive":28,"metrics":["F1@50%","F1@25%","F1@10%","Acc","Edit"],"first_row_in_archive_order":{"model":"Br-Prompt+ASPnet (RGB, flow, accelerometer)","paper_title":"ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources","paper_url":"/paper/aspnet-action-segmentation-with-shared","paper_date":"2023-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-gtea-1","slug":"action-segmentation-on-gtea-1","dataset":"GTEA","dataset_url":"/dataset/gtea","rows_in_archive":28,"metrics":["F1@50%","F1@25%","F1@10%","Acc","Edit"],"first_row_in_archive_order":{"model":"Semantic2Graph","paper_title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","paper_url":"/paper/semantic2graph-graph-based-multi-modal","paper_date":"2022-09-13","arxiv_id":"2209.05653","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-coin","slug":"action-segmentation-on-coin","dataset":"COIN","dataset_url":"/dataset/coin","rows_in_archive":9,"metrics":["Frame accuracy"],"first_row_in_archive_order":{"model":"UnLoc-L","paper_title":"UnLoc: A Unified Framework for Video Localization Tasks","paper_url":"/paper/unloc-a-unified-framework-for-video","paper_date":"2023-08-21","arxiv_id":"2308.11062","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"}],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-assembly101","slug":"action-segmentation-on-assembly101","dataset":"Assembly101","dataset_url":"/dataset/assembly101","rows_in_archive":7,"metrics":["F1@10%","F1@25%","F1@50%","Edit","MoF"],"first_row_in_archive_order":{"model":"ASQuery","paper_title":"ASQuery: A Query-based Model for Action Segmentation","paper_url":"/paper/asquery-a-query-based-model-for-action","paper_date":"2024-09-30","arxiv_id":null,"code_links":[{"title":"zlngan/ASQuery","url":"https://github.com/zlngan/ASQuery"}],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-jigsaws","slug":"action-segmentation-on-jigsaws","dataset":"JIGSAWS","dataset_url":"/dataset/jigsaws","rows_in_archive":7,"metrics":["Edit Distance","Accuracy","F1@10","F1@25","F1@50"],"first_row_in_archive_order":{"model":"MRG-Net","paper_title":"Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery","paper_url":"/paper/relational-graph-learning-on-visual-and","paper_date":"2020-11-03","arxiv_id":"2011.01619","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-youtube-inria","slug":"action-segmentation-on-youtube-inria","dataset":"Youtube INRIA Instructional","dataset_url":"/dataset/youtube-inria-instructional","rows_in_archive":2,"metrics":["Acc","F1"],"first_row_in_archive_order":{"model":"TSA (FINCH)","paper_title":"Leveraging triplet loss for unsupervised action segmentation","paper_url":"/paper/leveraging-triplet-loss-for-unsupervised","paper_date":"2023-04-13","arxiv_id":"2304.06403","code_links":[{"title":"elenabbbuenob/tsa-actionseg","url":"https://github.com/elenabbbuenob/tsa-actionseg"}],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-50salads","slug":"action-segmentation-on-50salads","dataset":"50Salads","dataset_url":null,"rows_in_archive":1,"metrics":["Acc","Edit","F1@10%","F1@25%","F1@50%"],"first_row_in_archive_order":{"model":"EUT","paper_title":"Do we really need temporal convolutions in action segmentation?","paper_url":"/paper/efficient-u-transformer-with-boundary-aware","paper_date":"2022-05-26","arxiv_id":"2205.13425","code_links":[{"title":"ddz16/TUT","url":"https://github.com/ddz16/TUT"}],"syntology":null}},{"leaderboard":"/sota/action-segmentation-on-mpii-cooking-2-dataset","slug":"action-segmentation-on-mpii-cooking-2-dataset","dataset":"MPII Cooking 2 Dataset","dataset_url":"/dataset/mpii-cooking-2-dataset","rows_in_archive":1,"metrics":["Accuracy","mIoU"],"first_row_in_archive_order":{"model":"Unsup. TW-FINCH (K=avg/activity)","paper_title":"Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation","paper_url":"/paper/temporally-weighted-hierarchical-clustering","paper_date":"2021-03-20","arxiv_id":"2103.11264","code_links":[{"title":"ssarfraz/FINCH-CLustering","url":"https://github.com/ssarfraz/FINCH-CLustering"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}}}],"datasets":[{"url":"/dataset/breakfast","name":"Breakfast","full_name":"The Breakfast Actions Dataset","num_papers_in_archive":179},{"url":"/dataset/gtea","name":"GTEA","full_name":"Georgia Tech Egocentric Activity","num_papers_in_archive":120},{"url":"/dataset/coin","name":"COIN","full_name":"","num_papers_in_archive":105},{"url":"/dataset/jigsaws","name":"JIGSAWS","full_name":"JHU-ISI Gesture and Skill Assessment Working Set","num_papers_in_archive":105},{"url":"/dataset/assembly101","name":"Assembly101","full_name":"","num_papers_in_archive":57},{"url":"/dataset/50-salads","name":"50 Salads","full_name":"","num_papers_in_archive":35},{"url":"/dataset/hoi4d","name":"HOI4D","full_name":"","num_papers_in_archive":23},{"url":"/dataset/watch-n-patch","name":"Watch-n-Patch","full_name":"Watch-n-Patch","num_papers_in_archive":13},{"url":"/dataset/egoexolearn","name":"EgoExoLearn","full_name":"","num_papers_in_archive":12},{"url":"/dataset/egoprocel","name":"EgoProceL","full_name":"","num_papers_in_archive":9},{"url":"/dataset/youtube-inria-instructional","name":"Youtube INRIA Instructional","full_name":"Unsupervised learning from narrated instruction videos","num_papers_in_archive":8},{"url":"/dataset/tum-kitchen","name":"TUM Kitchen","full_name":"TUM Kitchen","num_papers_in_archive":7},{"url":"/dataset/mpii-cooking-2-dataset","name":"MPII Cooking 2 Dataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/ha-vid","name":"HA-ViD","full_name":"HA-ViD: A Human Assembly Video Dataset","num_papers_in_archive":1},{"url":"/dataset/inhard","name":"InHARD","full_name":"Industrial Human Action Recognition Dataset in the Context of Industrial Collaborative Robotics","num_papers_in_archive":1},{"url":"/dataset/lara","name":"LARa","full_name":"Logistic Activity Recognition Challenge","num_papers_in_archive":1},{"url":"/dataset/uw-iom","name":"UW IOM","full_name":"University of Washington Indoor Object Manipulation","num_papers_in_archive":1},{"url":"/dataset/sics-155","name":"SICS-155","full_name":"Phase Recognition in Small Incision Cataract Surgery Videos","num_papers_in_archive":0}],"subtasks":[{"url":"/task/skeleton-based-action-segmentation","name":"Skeleton Based Action Segmentation"},{"url":"/task/unsupervised-action-segmentation","name":"Unsupervised Action Segmentation"},{"url":"/task/weakly-supervised-action-segmentation","name":"Weakly Supervised Action Segmentation (Transcript)"},{"url":"/task/weakly-supervised-action-segmentation-action","name":"Weakly Supervised Action Segmentation (Action Set))"}],"parent_tasks":[{"url":"/task/action-localization","name":"Action Localization"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":219,"of_with_code":99,"tagged_in_all":219,"counts":{"archive_papers_tagged":219,"with_a_code_link":99,"where_syntology_ran_a_sample":27,"not_listed_spam_title":0,"listed":219,"listed_where_code_ran":27,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":23,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":23,"listed_every_run_a_failure_of_syntologys_instrument":4,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/temporal-convolutional-networks-for-action","slug":"temporal-convolutional-networks-for-action","title":"Temporal Convolutional Networks for Action Segmentation and Detection","date":"2016-11-16","arxiv_id":"1611.05267","repositories_listed":5,"syntology":{"n":21,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/temporal-convolutional-networks-for-action#ran","syntology_url":"https://syntology.ai/paper/1611.05267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.05267"}},"official":null}},{"url":"/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","repositories_listed":4,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/hierarchical-neurosymbolic-approach-for","slug":"hierarchical-neurosymbolic-approach-for","title":"Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment","date":"2024-03-20","arxiv_id":"2403.13798","repositories_listed":3,"syntology":null},{"url":"/paper/temporal-action-segmentation-an-analysis-of","slug":"temporal-action-segmentation-an-analysis-of","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","date":"2022-10-19","arxiv_id":"2210.10352","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/temporal-action-segmentation-an-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2210.10352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10352"}},"official":{"repos":["atlas-eccv22/awesome-temporal-action-segmentation","nus-cvml/awesome-temporal-action-segmentation"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/logo-a-long-form-video-dataset-for-group-1","slug":"logo-a-long-form-video-dataset-for-group-1","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","date":"2024-04-07","arxiv_id":"2404.05029","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/logo-a-long-form-video-dataset-for-group-1#ran","syntology_url":"https://syntology.ai/paper/2404.05029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05029"}},"official":{"repos":["shiyi-zh0408/logo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/hopadiff-holistic-partial-aware-fourier","slug":"hopadiff-holistic-partial-aware-fourier","title":"HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios","date":"2025-06-11","arxiv_id":"2506.09650","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":6,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hopadiff-holistic-partial-aware-fourier#ran","syntology_url":"https://syntology.ai/paper/2506.09650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09650"}},"official":{"repos":["kpeng9510/hopadiff"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/epfl-smart-kitchen-30-densely-annotated","slug":"epfl-smart-kitchen-30-densely-annotated","title":"EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models","date":"2025-06-02","arxiv_id":"2506.01608","repositories_listed":1,"syntology":null},{"url":"/paper/cost-sensitive-learning-for-long-tailed","slug":"cost-sensitive-learning-for-long-tailed","title":"Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation","date":"2025-03-24","arxiv_id":"2503.18358","repositories_listed":1,"syntology":null},{"url":"/paper/mamba4d-efficient-4d-point-cloud-video","slug":"mamba4d-efficient-4d-point-cloud-video","title":"Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/onlinetas-an-online-baseline-for-temporal","slug":"onlinetas-an-online-baseline-for-temporal","title":"OnlineTAS: An Online Baseline for Temporal Action Segmentation","date":"2024-11-02","arxiv_id":"2411.01122","repositories_listed":1,"syntology":null},{"url":"/paper/language-assisted-skeleton-action","slug":"language-assisted-skeleton-action","title":"Language-Assisted Skeleton Action Understanding for Skeleton-Based Temporal Action Segmentation","date":"2024-10-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/promqa-question-answering-dataset-for","slug":"promqa-question-answering-dataset-for","title":"ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding","date":"2024-10-29","arxiv_id":"2410.22211","repositories_listed":1,"syntology":null},{"url":"/paper/language-assisted-human-part-motion-learning","slug":"language-assisted-human-part-motion-learning","title":"Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation","date":"2024-10-08","arxiv_id":"2410.06353","repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/transformer-with-controlled-attention-for","slug":"transformer-with-controlled-attention-for","title":"Transformer with Controlled Attention for Synchronous Motion Captioning","date":"2024-09-13","arxiv_id":"2409.09177","repositories_listed":1,"syntology":null},{"url":"/paper/3d-pose-based-temporal-action-segmentation","slug":"3d-pose-based-temporal-action-segmentation","title":"3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach","date":"2024-08-29","arxiv_id":"2408.16638","repositories_listed":1,"syntology":null},{"url":"/paper/long-tail-temporal-action-segmentation-with","slug":"long-tail-temporal-action-segmentation-with","title":"Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment","date":"2024-08-19","arxiv_id":"2408.09919","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-animal-action-segmentation","slug":"a-study-of-animal-action-segmentation","title":"A study of animal action segmentation algorithms across supervised, unsupervised, and semi-supervised learning paradigms","date":"2024-07-23","arxiv_id":"2407.16727","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/snippet-aware-transformer-with-multiple","slug":"snippet-aware-transformer-with-multiple","title":"Snippet-Aware Transformer With Multiple Action Elements for Skeleton-Based Action Segmentation","date":"2024-05-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-and-effective-weakly-supervised","slug":"efficient-and-effective-weakly-supervised","title":"Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment","date":"2024-03-28","arxiv_id":"2403.19225","repositories_listed":1,"syntology":null},{"url":"/paper/a-multimodal-handover-failure-detection","slug":"a-multimodal-handover-failure-detection","title":"A Multimodal Handover Failure Detection Dataset and Baselines","date":"2024-02-28","arxiv_id":"2402.18319","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","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"}},"official":null}},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/progress-aware-online-action-segmentation-for","slug":"progress-aware-online-action-segmentation-for","title":"Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/smc-nca-semantic-guided-multi-level-contrast","slug":"smc-nca-semantic-guided-multi-level-contrast","title":"SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentation","date":"2023-12-19","arxiv_id":"2312.12347","repositories_listed":1,"syntology":null},{"url":"/paper/x4d-sceneformer-enhanced-scene-understanding","slug":"x4d-sceneformer-enhanced-scene-understanding","title":"X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer","date":"2023-12-12","arxiv_id":"2312.07378","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/x4d-sceneformer-enhanced-scene-understanding#ran","syntology_url":"https://syntology.ai/paper/2312.07378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07378"}},"official":{"repos":["jinglinglingling/x4d"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-decoupled-spatio-temporal-framework-for","slug":"a-decoupled-spatio-temporal-framework-for","title":"A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation","date":"2023-12-10","arxiv_id":"2312.05830","repositories_listed":1,"syntology":null},{"url":"/paper/activity-grammars-for-temporal-action-1","slug":"activity-grammars-for-temporal-action-1","title":"Activity Grammars for Temporal Action Segmentation","date":"2023-12-07","arxiv_id":"2312.04266","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/activity-grammars-for-temporal-action-1#ran","syntology_url":"https://syntology.ai/paper/2312.04266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04266"}},"official":{"repos":["gongda0e/kari"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sigformer-sparse-signal-guided-transformer","slug":"sigformer-sparse-signal-guided-transformer","title":"SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation","date":"2023-11-29","arxiv_id":"2311.17428","repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-streaming-video-temporal-action","slug":"end-to-end-streaming-video-temporal-action","title":"End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning","date":"2023-09-27","arxiv_id":"2309.15683","repositories_listed":1,"syntology":null},{"url":"/paper/otas-unsupervised-boundary-detection-for","slug":"otas-unsupervised-boundary-detection-for","title":"OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation","date":"2023-09-12","arxiv_id":"2309.06276","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/ha-vid-a-human-assembly-video-dataset-for","slug":"ha-vid-a-human-assembly-video-dataset-for","title":"HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding","date":"2023-07-09","arxiv_id":"2307.05721","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":9,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ha-vid-a-human-assembly-video-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2307.05721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05721"}},"official":{"repos":["iai-hrc/ha-vid"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/pretrained-language-models-as-visual-planners","slug":"pretrained-language-models-as-visual-planners","title":"Pretrained Language Models as Visual Planners for Human Assistance","date":"2023-04-17","arxiv_id":"2304.09179","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-action-segmentation","slug":"diffusion-action-segmentation","title":"Diffusion Action Segmentation","date":"2023-03-31","arxiv_id":"2303.17959","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}},{"url":"/paper/kinematic-data-based-action-segmentation-for","slug":"kinematic-data-based-action-segmentation-for","title":"MS-TCRNet: Multi-Stage Temporal Convolutional Recurrent Networks for Action Segmentation Using Sensor-Augmented Kinematics","date":"2023-03-14","arxiv_id":"2303.07814","repositories_listed":1,"syntology":null},{"url":"/paper/timestamp-supervised-action-segmentation-in","slug":"timestamp-supervised-action-segmentation-in","title":"Timestamp-Supervised Action Segmentation from the Perspective of Clustering","date":"2022-12-22","arxiv_id":"2212.11694","repositories_listed":1,"syntology":null},{"url":"/paper/streaming-video-temporal-action-segmentation","slug":"streaming-video-temporal-action-segmentation","title":"Streaming Video Temporal Action Segmentation In Real Time","date":"2022-09-28","arxiv_id":"2209.13808","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-alignment-networks-for-long-term","slug":"temporal-alignment-networks-for-long-term","title":"Temporal Alignment Networks for Long-term Video","date":"2022-04-06","arxiv_id":"2204.02968","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-alignment-networks-for-long-term#ran","syntology_url":"https://syntology.ai/paper/2204.02968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02968"}},"official":null}},{"url":"/paper/assembly101-a-large-scale-multi-view-video","slug":"assembly101-a-large-scale-multi-view-video","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","date":"2022-03-28","arxiv_id":"2203.14712","repositories_listed":1,"syntology":null},{"url":"/paper/bridge-prompt-towards-ordinal-action","slug":"bridge-prompt-towards-ordinal-action","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","date":"2022-03-26","arxiv_id":"2203.14104","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bridge-prompt-towards-ordinal-action#ran","syntology_url":"https://syntology.ai/paper/2203.14104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14104"}},"official":{"repos":["ttlmh/bridge-prompt"],"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"]}}},{"url":"/paper/hoi4d-a-4d-egocentric-dataset-for-category","slug":"hoi4d-a-4d-egocentric-dataset-for-category","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","date":"2022-03-03","arxiv_id":"2203.01577","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hoi4d-a-4d-egocentric-dataset-for-category#ran","syntology_url":"https://syntology.ai/paper/2203.01577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01577"}},"official":{"repos":["leolyliu/HOI4D-Instructions"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skeleton-based-action-segmentation-with-multi","slug":"skeleton-based-action-segmentation-with-multi","title":"Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks","date":"2022-02-03","arxiv_id":"2202.01727","repositories_listed":1,"syntology":null},{"url":"/paper/semi-weakly-supervised-learning-of-complex","slug":"semi-weakly-supervised-learning-of-complex","title":"Semi-Weakly-Supervised Learning of Complex Actions From Instructional Task Videos","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/you-can-wash-better-daily-handwashing","slug":"you-can-wash-better-daily-handwashing","title":"You Can Wash Hands Better: Accurate Daily Handwashing Assessment with a Smartwatch","date":"2021-12-09","arxiv_id":"2112.06657","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-frame-level-representation-learning","slug":"iterative-frame-level-representation-learning","title":"Iterative Contrast-Classify For Semi-supervised Temporal Action Segmentation","date":"2021-12-02","arxiv_id":"2112.01402","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/iterative-frame-level-representation-learning#ran","syntology_url":"https://syntology.ai/paper/2112.01402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01402"}},"official":{"repos":["dipika-singhania/ICC-Semi-Supervised-TAS"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-tokenized-human-dynamics","slug":"towards-tokenized-human-dynamics","title":"Towards Tokenized Human Dynamics Representation","date":"2021-11-22","arxiv_id":"2111.11433","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-temporal-action-localization-with","slug":"few-shot-temporal-action-localization-with","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","date":"2021-10-20","arxiv_id":"2110.10552","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/hierarchical-modeling-for-task-recognition","slug":"hierarchical-modeling-for-task-recognition","title":"Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos","date":"2021-10-12","arxiv_id":"2110.05697","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/automated-freezing-of-gait-assessment-with","slug":"automated-freezing-of-gait-assessment-with","title":"Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks","date":"2021-03-29","arxiv_id":"2103.15449","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/learning-discriminative-prototypes-with","slug":"learning-discriminative-prototypes-with","title":"Learning Discriminative Prototypes with Dynamic Time Warping","date":"2021-03-17","arxiv_id":"2103.09458","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/learning-discriminative-prototypes-with#ran","syntology_url":"https://syntology.ai/paper/2103.09458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.09458"}},"official":{"repos":["BorealisAI/TSC-Disc-Proto"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-action-segmentation-from-timestamp","slug":"temporal-action-segmentation-from-timestamp","title":"Temporal Action Segmentation from Timestamp Supervision","date":"2021-03-11","arxiv_id":"2103.06669","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/temporal-action-segmentation-from-timestamp#ran","syntology_url":"https://syntology.ai/paper/2103.06669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06669"}},"official":{"repos":["ZheLi2020/TimestampActionSeg"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/alleviating-class-wise-gradient-imbalance-for","slug":"alleviating-class-wise-gradient-imbalance-for","title":"Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation","date":"2020-11-24","arxiv_id":"2011.11952","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/online-spatiotemporal-action-detection-and","slug":"online-spatiotemporal-action-detection-and","title":"Online Spatiotemporal Action Detection and Prediction via Causal Representations","date":"2020-08-31","arxiv_id":"2008.13759","repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-segment-actions-from-observation","slug":"learning-to-segment-actions-from-observation","title":"Learning to Segment Actions from Observation and Narration","date":"2020-05-07","arxiv_id":"2005.03684","repositories_listed":1,"syntology":null},{"url":"/paper/sct-set-constrained-temporal-transformer-for","slug":"sct-set-constrained-temporal-transformer-for","title":"SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation","date":"2020-03-31","arxiv_id":"2003.14266","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/low-rank-random-tensor-for-bilinear-pooling","slug":"low-rank-random-tensor-for-bilinear-pooling","title":"Frontal Low-rank Random Tensors for Fine-grained Action Segmentation","date":"2019-06-03","arxiv_id":"1906.01004","repositories_listed":1,"syntology":null},{"url":"/paper/190411953","slug":"190411953","title":"Temporal Unet: Sample Level Human Action Recognition using WiFi","date":"2019-04-19","arxiv_id":"1904.11953","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-ergonomic-risks-during-indoor","slug":"predicting-ergonomic-risks-during-indoor","title":"Toward Ergonomic Risk Prediction via Segmentation of Indoor Object Manipulation Actions Using Spatiotemporal Convolutional Networks","date":"2019-02-14","arxiv_id":"1902.05176","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-surgical","slug":"deep-reinforcement-learning-for-surgical","title":"Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification","date":"2018-06-21","arxiv_id":"1806.08089","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-segmentation-with","slug":"weakly-supervised-action-segmentation-with","title":"Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment","date":"2018-03-28","arxiv_id":"1803.10699","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/weakly-supervised-action-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/1803.10699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10699"}},"official":{"repos":["ld-ing/TCFPN-ISBA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/actor-and-action-video-segmentation-from-a","slug":"actor-and-action-video-segmentation-from-a","title":"Actor and Action Video Segmentation from a Sentence","date":"2018-03-20","arxiv_id":"1803.07485","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-human-action-segmentation-via","slug":"temporal-human-action-segmentation-via","title":"Temporal Human Action Segmentation via Dynamic Clustering","date":"2018-03-15","arxiv_id":"1803.05790","repositories_listed":1,"syntology":null},{"url":"/paper/action-sets-weakly-supervised-action","slug":"action-sets-weakly-supervised-action","title":"Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints","date":"2017-06-02","arxiv_id":"1706.00699","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-learning-with-rnn","slug":"weakly-supervised-action-learning-with-rnn","title":"Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling","date":"2017-03-23","arxiv_id":"1703.08132","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-convolutional-networks-a-unified","slug":"temporal-convolutional-networks-a-unified","title":"Temporal Convolutional Networks: A Unified Approach to Action Segmentation","date":"2016-08-29","arxiv_id":"1608.08242","repositories_listed":1,"syntology":null},{"url":null,"slug":"self-supervised-pretraining-of-vision","title":"Self-supervised pretraining of vision transformers for animal behavioral analysis and neural encoding","date":"2025-07-13","arxiv_id":"2507.09513","repositories_listed":0,"syntology":null}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/action-segmentation-on-assembly101","since_archive":"/sota/action-segmentation-on-assembly101#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":27,"papers_where_code_ran_first_page":"/task/action-segmentation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/action-segmentation/papers/2","json":"/task/action-segmentation/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/action-segmentation/papers/3","json":"/task/action-segmentation/papers/3.json","rows":19},{"order":"ran","page":1,"of":1,"url":"/task/action-segmentation/papers/ran/1","json":"/task/action-segmentation/papers/ran/1.json","rows":27}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"d1db551bdd0473ec8fd594c3773d919b2c903d42395992069b7150334664a4a2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}