{"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-detection","name":"Action Detection","slug":"action-detection","description_markdown":"Action Detection aims to find both where and when an action occurs within a video clip and classify what the action is taking place. Typically results are given in the form of action tublets, which are action bounding boxes linked across time in the video. This is related to temporal localization, which seeks to identify the start and end frame of an action, and action recognition,  which seeks only to classify which action is taking place and typically assumes a trimmed video.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":817,"papers_with_code":277,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"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":34,"subtasks":8,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/action-detection-on-ucf101-24","slug":"action-detection-on-ucf101-24","dataset":"UCF101-24","dataset_url":"/dataset/ucf101-24","rows_in_archive":19,"metrics":["Frame-mAP 0.5","Video-mAP 0.1","Video-mAP 0.2","Video-mAP 0.5"],"first_row_in_archive_order":{"model":"STAR/L","paper_title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","paper_url":"/paper/end-to-end-spatio-temporal-action","paper_date":"2023-04-24","arxiv_id":"2304.12160","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-detection-on-j-hmdb","slug":"action-detection-on-j-hmdb","dataset":"J-HMDB","dataset_url":"/dataset/jhmdb","rows_in_archive":18,"metrics":["Frame-mAP 0.5","Video-mAP 0.2","Video-mAP 0.5"],"first_row_in_archive_order":{"model":"SiA","paper_title":"Scaling Open-Vocabulary Action Detection","paper_url":"/paper/scaling-open-vocabulary-action-detection","paper_date":"2025-04-04","arxiv_id":"2504.03096","code_links":[{"title":"siatheindochinese/sia_act_placeholder","url":"https://github.com/siatheindochinese/sia_act_placeholder"}],"syntology":null}},{"leaderboard":"/sota/action-detection-on-charades","slug":"action-detection-on-charades","dataset":"Charades","dataset_url":"/dataset/charades","rows_in_archive":16,"metrics":["mAP"],"first_row_in_archive_order":{"model":"TTM","paper_title":"Token Turing Machines","paper_url":"/paper/token-turing-machines","paper_date":"2022-11-16","arxiv_id":"2211.09119","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"}],"syntology":null}},{"leaderboard":"/sota/action-detection-on-multi-thumos","slug":"action-detection-on-multi-thumos","dataset":"Multi-THUMOS","dataset_url":"/dataset/multithumos","rows_in_archive":8,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MLAD","paper_title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","paper_url":"/paper/modeling-multi-label-action-dependencies-for","paper_date":"2021-03-04","arxiv_id":"2103.03027","code_links":[{"title":"ptirupat/MLAD","url":"https://github.com/ptirupat/MLAD"}],"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modeling-multi-label-action-dependencies-for#ran","syntology_url":"https://syntology.ai/paper/2103.03027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03027"}},"official":{"repos":["ptirupat/MLAD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/action-detection-on-ucf-sports","slug":"action-detection-on-ucf-sports","dataset":"UCF Sports","dataset_url":"/dataset/ucf-sports","rows_in_archive":7,"metrics":["Frame-mAP 0.5","Video-mAP 0.2","Video-mAP 0.5"],"first_row_in_archive_order":{"model":"T-CNN","paper_title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","paper_url":"/paper/tube-convolutional-neural-network-t-cnn-for","paper_date":"2017-03-30","arxiv_id":"1703.10664","code_links":[{"title":"cyberpunk317/Action_detection","url":"https://github.com/cyberpunk317/Action_detection"}],"syntology":null}},{"leaderboard":"/sota/action-detection-on-thumos-14","slug":"action-detection-on-thumos-14","dataset":"THUMOS' 14","dataset_url":"/dataset/thumos14-1","rows_in_archive":4,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MAT (Ours) Trans","paper_title":"Memory-and-Anticipation Transformer for Online Action Understanding","paper_url":"/paper/memory-and-anticipation-transformer-for","paper_date":"2023-08-15","arxiv_id":"2308.07893","code_links":[{"title":"echo0125/memory-and-anticipation-transformer","url":"https://github.com/echo0125/memory-and-anticipation-transformer"}],"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/memory-and-anticipation-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2308.07893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07893"}},"official":{"repos":["echo0125/memory-and-anticipation-transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/action-detection-on-multisports","slug":"action-detection-on-multisports","dataset":"MultiSports","dataset_url":"/dataset/multisports","rows_in_archive":2,"metrics":["Frame-mAP 0.5","Video-mAP 0.2","Video-mAP 0.5"],"first_row_in_archive_order":{"model":"HIT","paper_title":"Holistic Interaction Transformer Network for Action Detection","paper_url":"/paper/holistic-interaction-transformer-network-for","paper_date":"2022-10-23","arxiv_id":"2210.12686","code_links":[{"title":"joslefaure/hit","url":"https://github.com/joslefaure/hit"}],"syntology":null}},{"leaderboard":"/sota/action-detection-on-tsu","slug":"action-detection-on-tsu","dataset":"TSU","dataset_url":"/dataset/tsu","rows_in_archive":2,"metrics":["Frame-mAP"],"first_row_in_archive_order":{"model":"PDAN","paper_title":"PDAN: Pyramid Dilated Attention Network for Action Detection","paper_url":"/paper/pdan-pyramid-dilated-attention-network-for","paper_date":"2021-01-05","arxiv_id":null,"code_links":[{"title":"dairui01/PDAN","url":"https://github.com/dairui01/PDAN"}],"syntology":null}},{"leaderboard":"/sota/action-detection-on-ttstroke-21","slug":"action-detection-on-ttstroke-21","dataset":"TTStroke-21 ME22","dataset_url":"/dataset/ttstroke-21","rows_in_archive":2,"metrics":["IoU","mAP"],"first_row_in_archive_order":{"model":"STCNN-V2 (Vote decision)","paper_title":"Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms","paper_url":"/paper/baseline-method-for-the-sport-task-of","paper_date":"2023-02-06","arxiv_id":"2302.02752","code_links":[{"title":"ccp-eva/sporttaskme22","url":"https://github.com/ccp-eva/sporttaskme22"}],"syntology":null}},{"leaderboard":"/sota/action-detection-on-ttstroke-21-me21","slug":"action-detection-on-ttstroke-21-me21","dataset":"TTStroke-21 ME21","dataset_url":"/dataset/ttstroke-21-me21","rows_in_archive":2,"metrics":["IoU","mAP"],"first_row_in_archive_order":{"model":"STCNN","paper_title":"Spatio-Temporal CNN baseline method for the Sports Video Task of MediaEval 2021 benchmark","paper_url":"/paper/spatio-temporal-cnn-baseline-method-for-the","paper_date":"2021-12-16","arxiv_id":"2112.12074","code_links":[{"title":"ccp-eva/sporttaskme21","url":"https://github.com/ccp-eva/sporttaskme21"}],"syntology":null}},{"leaderboard":"/sota/action-detection-on-multithumos-1","slug":"action-detection-on-multithumos-1","dataset":"MultiTHUMOS","dataset_url":"/dataset/multithumos","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"PAT","paper_title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","paper_url":"/paper/pat-position-aware-transformer-for-dense","paper_date":"2023-08-09","arxiv_id":"2308.05051","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/charades","name":"Charades","full_name":"","num_papers_in_archive":428},{"url":"/dataset/thumos14-1","name":"THUMOS14","full_name":"","num_papers_in_archive":318},{"url":"/dataset/jhmdb","name":"JHMDB","full_name":"Joint-annotated Human Motion Data Base","num_papers_in_archive":249},{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/multithumos","name":"MultiTHUMOS","full_name":"","num_papers_in_archive":58},{"url":"/dataset/toyota-smarthome","name":"Toyota Smarthome Dataset","full_name":"","num_papers_in_archive":31},{"url":"/dataset/tvseries","name":"TVSeries","full_name":"","num_papers_in_archive":29},{"url":"/dataset/road","name":"ROAD","full_name":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","num_papers_in_archive":27},{"url":"/dataset/okutama-action","name":"Okutama-Action","full_name":"","num_papers_in_archive":24},{"url":"/dataset/multisports","name":"MultiSports","full_name":"","num_papers_in_archive":20},{"url":"/dataset/meva","name":"MEVA","full_name":"Multiview Extended Video with Activities","num_papers_in_archive":17},{"url":"/dataset/ucf101-24","name":"UCF101-24","full_name":"","num_papers_in_archive":17},{"url":"/dataset/tsu","name":"TSU","full_name":"Toyota Smarthome Untrimmed","num_papers_in_archive":16},{"url":"/dataset/ava-speech","name":"AVA-Speech","full_name":"","num_papers_in_archive":10},{"url":"/dataset/egoprocel","name":"EgoProceL","full_name":"","num_papers_in_archive":9},{"url":"/dataset/ucf-sports","name":"UCF Sports","full_name":"","num_papers_in_archive":9},{"url":"/dataset/urfd-dataset","name":"URFD Dataset","full_name":"UR Fall Detection Dataset","num_papers_in_archive":7},{"url":"/dataset/vidhoi","name":"VidHOI","full_name":"","num_papers_in_archive":7},{"url":"/dataset/iitb-corridor","name":"IITB Corridor","full_name":"","num_papers_in_archive":5},{"url":"/dataset/mlb-youtube-dataset","name":"MLB-YouTube Dataset","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/mpii-cooking-2-dataset","name":"MPII Cooking 2 Dataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/real-life-violence-situations-dataset","name":"Real Life Violence Situations Dataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/wear","name":"WEAR","full_name":"WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition","num_papers_in_archive":5},{"url":"/dataset/esad","name":"ESAD","full_name":"SARAS Endoscopic Surgeon Action Detection","num_papers_in_archive":4},{"url":"/dataset/oreba","name":"OREBA","full_name":"Objectively Recognizing Eating Behavior and Associated Intake","num_papers_in_archive":3},{"url":"/dataset/ttstroke-21-me21","name":"TTStroke-21 ME21","full_name":"TTStroke-21 for MediaEval 2021","num_papers_in_archive":3},{"url":"/dataset/ttstroke-21","name":"TTStroke-21 ME22","full_name":"TTStroke-21 for MediaEval 2022","num_papers_in_archive":3},{"url":"/dataset/ucla-protest-image","name":"UCLA Protest Image","full_name":"","num_papers_in_archive":2},{"url":"/dataset/capture-24","name":"Capture-24","full_name":"","num_papers_in_archive":1},{"url":"/dataset/custom-spatio-temporal-action-video-dataset","name":"Custom Spatio-Temporal Action Video Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/liris-human-activities-dataset","name":"LIRIS human activities dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mouse-grooming-behavior","name":"Mouse Grooming Behavior","full_name":"","num_papers_in_archive":1},{"url":"/dataset/infiniterep","name":"InfiniteRep","full_name":"InfiniteRep","num_papers_in_archive":0}],"subtasks":[{"url":"/task/action-triplet-detection","name":"Action Triplet Detection"},{"url":"/task/audio-visual-active-speaker-detection","name":"Audio-Visual Active Speaker Detection"},{"url":"/task/few-shot-temporal-action-localization","name":"Few Shot Temporal Action Localization"},{"url":"/task/fine-grained-action-detection","name":"Fine-Grained Action Detection"},{"url":"/task/human-activity-recognition","name":"Human Activity Recognition"},{"url":"/task/multiple-action-detection","name":"Multiple Action Detection"},{"url":"/task/online-action-detection","name":"Online Action Detection"},{"url":"/task/skeleton-based-action-recognition","name":"Skeleton Based Action Recognition"}],"parent_tasks":[],"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":9,"rows_per_page":100,"shown":100,"of":817,"of_with_code":277,"tagged_in_all":817,"counts":{"archive_papers_tagged":817,"with_a_code_link":277,"where_syntology_ran_a_sample":53,"not_listed_spam_title":0,"listed":817,"listed_where_code_ran":53,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":46,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":46,"listed_every_run_a_failure_of_syntologys_instrument":7,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers 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/continuous-control-with-deep-reinforcement","slug":"continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","arxiv_id":"1509.02971","repositories_listed":161,"syntology":{"n":306,"n_ran":163,"n_constructed":126,"n_ran_checked":152,"n_instrument":11,"n_unverified":143,"n_honours":3,"n_violates":0,"n_no_contract":149,"n_pointer_only":163,"phrase":"163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified","sample_list":"/paper/continuous-control-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"}},"official":null}},{"url":"/paper/bsn-boundary-sensitive-network-for-temporal","slug":"bsn-boundary-sensitive-network-for-temporal","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","date":"2018-06-08","arxiv_id":"1806.02964","repositories_listed":17,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bsn-boundary-sensitive-network-for-temporal#ran","syntology_url":"https://syntology.ai/paper/1806.02964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02964"}},"official":{"repos":["wzmsltw/BSN-boundary-sensitive-network.pytorch"],"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/bmn-boundary-matching-network-for-temporal","slug":"bmn-boundary-matching-network-for-temporal","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","date":"2019-07-23","arxiv_id":"1907.09702","repositories_listed":15,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bmn-boundary-matching-network-for-temporal#ran","syntology_url":"https://syntology.ai/paper/1907.09702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09702"}},"official":{"repos":["PaddlePaddle/models"],"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/slowfast-networks-for-video-recognition","slug":"slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","repositories_listed":15,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}},"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/ava-a-video-dataset-of-spatio-temporally","slug":"ava-a-video-dataset-of-spatio-temporally","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","date":"2017-05-23","arxiv_id":"1705.08421","repositories_listed":9,"syntology":null},{"url":"/paper/rescaling-egocentric-vision","slug":"rescaling-egocentric-vision","title":"Rescaling Egocentric Vision","date":"2020-06-23","arxiv_id":"2006.13256","repositories_listed":7,"syntology":{"n":18,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/rescaling-egocentric-vision#ran","syntology_url":"https://syntology.ai/paper/2006.13256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13256"}},"official":{"repos":["epic-kitchens/epic-kitchens-100-narrator","epic-kitchens/epic-kitchens-100-annotations"],"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/cholectriplet2021-a-benchmark-challenge-for","slug":"cholectriplet2021-a-benchmark-challenge-for","title":"CholecTriplet2021: A benchmark challenge for surgical action triplet recognition","date":"2022-04-10","arxiv_id":"2204.04746","repositories_listed":6,"syntology":null},{"url":"/paper/temporal-action-detection-with-structured","slug":"temporal-action-detection-with-structured","title":"Temporal Action Detection with Structured Segment Networks","date":"2017-04-20","arxiv_id":"1704.06228","repositories_listed":6,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/temporal-action-detection-with-structured#ran","syntology_url":"https://syntology.ai/paper/1704.06228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.06228"}},"official":{"repos":["open-mmlab/mmaction"],"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/you-only-watch-once-a-unified-cnn","slug":"you-only-watch-once-a-unified-cnn","title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","date":"2019-11-15","arxiv_id":"1911.06644","repositories_listed":5,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/you-only-watch-once-a-unified-cnn#ran","syntology_url":"https://syntology.ai/paper/1911.06644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06644"}},"official":{"repos":["wei-tim/YOWO"],"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/joint-analysis-and-prediction-of-human","slug":"joint-analysis-and-prediction-of-human","title":"From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video","date":"2020-11-20","arxiv_id":"2011.10670","repositories_listed":4,"syntology":null},{"url":"/paper/hake-human-activity-knowledge-engine","slug":"hake-human-activity-knowledge-engine","title":"HAKE: Human Activity Knowledge Engine","date":"2019-04-13","arxiv_id":"1904.06539","repositories_listed":4,"syntology":null},{"url":"/paper/locally-consistent-deformable-convolution","slug":"locally-consistent-deformable-convolution","title":"Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection","date":"2018-11-21","arxiv_id":"1811.08815","repositories_listed":4,"syntology":null},{"url":"/paper/moshi-a-speech-text-foundation-model-for-real","slug":"moshi-a-speech-text-foundation-model-for-real","title":"Moshi: a speech-text foundation model for real-time dialogue","date":"2024-09-17","arxiv_id":"2410.00037","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moshi-a-speech-text-foundation-model-for-real#ran","syntology_url":"https://syntology.ai/paper/2410.00037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00037"}},"official":{"repos":["kyutai-labs/moshi"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/no-time-to-waste-squeeze-time-into-channel","slug":"no-time-to-waste-squeeze-time-into-channel","title":"No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding","date":"2024-05-14","arxiv_id":"2405.08344","repositories_listed":3,"syntology":null},{"url":"/paper/temporal-action-localization-with-enhanced","slug":"temporal-action-localization-with-enhanced","title":"Temporal Action Localization with Enhanced Instant Discriminability","date":"2023-09-11","arxiv_id":"2309.05590","repositories_listed":3,"syntology":null},{"url":"/paper/multi-speaker-and-wide-band-simulated","slug":"multi-speaker-and-wide-band-simulated","title":"Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization","date":"2022-11-12","arxiv_id":"2211.06750","repositories_listed":3,"syntology":null},{"url":"/paper/road-the-road-event-awareness-dataset-for","slug":"road-the-road-event-awareness-dataset-for","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","date":"2021-02-23","arxiv_id":"2102.11585","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/road-the-road-event-awareness-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2102.11585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11585"}},"official":{"repos":["gurkirt/3D-RetinaNet","gurkirt/road-dataset"],"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/context-aware-rcnn-a-baseline-for-action","slug":"context-aware-rcnn-a-baseline-for-action","title":"Context-Aware RCNN: A Baseline for Action Detection in Videos","date":"2020-07-20","arxiv_id":"2007.09861","repositories_listed":3,"syntology":null},{"url":"/paper/actor-context-actor-relation-network-for","slug":"actor-context-actor-relation-network-for","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","date":"2020-06-14","arxiv_id":"2006.07976","repositories_listed":3,"syntology":{"n":27,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":10,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/actor-context-actor-relation-network-for#ran","syntology_url":"https://syntology.ai/paper/2006.07976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07976"}},"official":{"repos":["Siyu-C/ACAR-Net"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":9,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-multigrid-method-for-efficiently-training","slug":"a-multigrid-method-for-efficiently-training","title":"A Multigrid Method for Efficiently Training Video Models","date":"2019-12-02","arxiv_id":"1912.00998","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-multigrid-method-for-efficiently-training#ran","syntology_url":"https://syntology.ai/paper/1912.00998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00998"}},"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pyannoteaudio-neural-building-blocks-for","slug":"pyannoteaudio-neural-building-blocks-for","title":"pyannote.audio: neural building blocks for speaker diarization","date":"2019-11-04","arxiv_id":"1911.01255","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/pyannoteaudio-neural-building-blocks-for#ran","syntology_url":"https://syntology.ai/paper/1911.01255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01255"}},"official":{"repos":["pyannote/pyannote-audio"],"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":["official"]}}},{"url":"/paper/rvad-an-unsupervised-segment-based-robust","slug":"rvad-an-unsupervised-segment-based-robust","title":"rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method","date":"2019-06-09","arxiv_id":"1906.03588","repositories_listed":3,"syntology":null},{"url":"/paper/fine-grained-activity-recognition-in-baseball","slug":"fine-grained-activity-recognition-in-baseball","title":"Fine-grained Activity Recognition in Baseball Videos","date":"2018-04-09","arxiv_id":"1804.03247","repositories_listed":3,"syntology":null},{"url":"/paper/r-c3d-region-convolutional-3d-network-for","slug":"r-c3d-region-convolutional-3d-network-for","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","date":"2017-03-22","arxiv_id":"1703.07814","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/r-c3d-region-convolutional-3d-network-for#ran","syntology_url":"https://syntology.ai/paper/1703.07814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.07814"}},"official":{"repos":["VisionLearningGroup/R-C3D"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/an-end-to-end-architecture-for-keyword","slug":"an-end-to-end-architecture-for-keyword","title":"An End-to-End Architecture for Keyword Spotting and Voice Activity Detection","date":"2016-11-28","arxiv_id":"1611.09405","repositories_listed":3,"syntology":null},{"url":"/paper/temporal-activity-detection-in-untrimmed","slug":"temporal-activity-detection-in-untrimmed","title":"Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks","date":"2016-08-29","arxiv_id":"1608.08128","repositories_listed":3,"syntology":null},{"url":"/paper/stable-mean-teacher-for-semi-supervised-video","slug":"stable-mean-teacher-for-semi-supervised-video","title":"Stable Mean Teacher for Semi-supervised Video Action Detection","date":"2024-12-10","arxiv_id":"2412.07072","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/stable-mean-teacher-for-semi-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2412.07072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07072"}},"official":{"repos":["AKASH2907/stable-mean-teacher","akash2907/stable_mean_teacher"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/action-ood-an-end-to-end-skeleton-based-model","slug":"action-ood-an-end-to-end-skeleton-based-model","title":"Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection","date":"2024-05-31","arxiv_id":"2405.20633","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-temporal-action-detection-with-1b","slug":"end-to-end-temporal-action-detection-with-1b","title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","date":"2023-11-28","arxiv_id":"2311.17241","repositories_listed":2,"syntology":null},{"url":"/paper/ivrit-ai-a-comprehensive-dataset-of-hebrew","slug":"ivrit-ai-a-comprehensive-dataset-of-hebrew","title":"ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and Development","date":"2023-07-17","arxiv_id":"2307.08720","repositories_listed":2,"syntology":null},{"url":"/paper/act3d-infinite-resolution-action-detection","slug":"act3d-infinite-resolution-action-detection","title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","date":"2023-06-30","arxiv_id":"2306.17817","repositories_listed":2,"syntology":null},{"url":"/paper/fha-kitchens-a-novel-dataset-for-fine-grained","slug":"fha-kitchens-a-novel-dataset-for-fine-grained","title":"Multi-Granularity Hand Action Detection","date":"2023-06-19","arxiv_id":"2306.10858","repositories_listed":2,"syntology":null},{"url":"/paper/shuttleset-a-human-annotated-stroke-level","slug":"shuttleset-a-human-annotated-stroke-level","title":"ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis","date":"2023-06-08","arxiv_id":"2306.04948","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-video-action-detection-with-token","slug":"efficient-video-action-detection-with-token","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","date":"2023-04-17","arxiv_id":"2304.08451","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/efficient-video-action-detection-with-token#ran","syntology_url":"https://syntology.ai/paper/2304.08451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08451"}},"official":{"repos":["mcg-nju/evad"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spotting-temporally-precise-fine-grained","slug":"spotting-temporally-precise-fine-grained","title":"Spotting Temporally Precise, Fine-Grained Events in Video","date":"2022-07-20","arxiv_id":"2207.10213","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 1 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/spotting-temporally-precise-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2207.10213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10213"}},"official":{"repos":["soccernet/sn-spotting","jhong93/spot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-action-detection-with-global","slug":"temporal-action-detection-with-global","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","date":"2022-07-14","arxiv_id":"2207.06580","repositories_listed":2,"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":3,"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/temporal-action-detection-with-global#ran","syntology_url":"https://syntology.ai/paper/2207.06580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06580"}},"official":{"repos":["sauradip/tags"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-attention-composition-for-temporal","slug":"structured-attention-composition-for-temporal","title":"Structured Attention Composition for Temporal Action Localization","date":"2022-05-20","arxiv_id":"2205.09956","repositories_listed":2,"syntology":null},{"url":"/paper/basictad-an-astounding-rgb-only-baseline-for","slug":"basictad-an-astounding-rgb-only-baseline-for","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","date":"2022-05-05","arxiv_id":"2205.02717","repositories_listed":2,"syntology":null},{"url":"/paper/speaker-embedding-aware-neural-diarization","slug":"speaker-embedding-aware-neural-diarization","title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information","date":"2021-11-28","arxiv_id":"2111.13694","repositories_listed":2,"syntology":null},{"url":"/paper/bertraffic-a-robust-bert-based-approach-for","slug":"bertraffic-a-robust-bert-based-approach-for","title":"BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications","date":"2021-10-12","arxiv_id":"2110.05781","repositories_listed":2,"syntology":null},{"url":"/paper/long-short-term-transformer-for-online-action","slug":"long-short-term-transformer-for-online-action","title":"Long Short-Term Transformer for Online Action Detection","date":"2021-07-07","arxiv_id":"2107.03377","repositories_listed":2,"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/long-short-term-transformer-for-online-action#ran","syntology_url":"https://syntology.ai/paper/2107.03377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03377"}},"official":{"repos":["amazon-research/long-short-term-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/end-to-end-speaker-segmentation-for-overlap","slug":"end-to-end-speaker-segmentation-for-overlap","title":"End-to-end speaker segmentation for overlap-aware resegmentation","date":"2021-04-08","arxiv_id":"2104.04045","repositories_listed":2,"syntology":null},{"url":"/paper/relaxed-transformer-decoders-for-direct","slug":"relaxed-transformer-decoders-for-direct","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","date":"2021-02-03","arxiv_id":"2102.01894","repositories_listed":2,"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":0,"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/relaxed-transformer-decoders-for-direct#ran","syntology_url":"https://syntology.ai/paper/2102.01894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.01894"}},"official":{"repos":["MCG-NJU/RTD-Action"],"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/generic-event-boundary-detection-a-benchmark","slug":"generic-event-boundary-detection-a-benchmark","title":"Generic Event Boundary Detection: A Benchmark for Event Segmentation","date":"2021-01-26","arxiv_id":"2101.10511","repositories_listed":2,"syntology":null},{"url":"/paper/voxlingua107-a-dataset-for-spoken-language-1","slug":"voxlingua107-a-dataset-for-spoken-language-1","title":"VoxLingua107: a Dataset for Spoken Language Recognition","date":"2020-11-25","arxiv_id":"2011.12998","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voxlingua107-a-dataset-for-spoken-language-1#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":{"repos":["alumae/torch-xvectors-wav"],"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"]}}},{"url":"/paper/asynchronous-interaction-aggregation-for","slug":"asynchronous-interaction-aggregation-for","title":"Asynchronous Interaction Aggregation for Action Detection","date":"2020-04-16","arxiv_id":"2004.07485","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/asynchronous-interaction-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2004.07485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07485"}},"official":{"repos":["MVIG-SJTU/AlphAction"],"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"]}}},{"url":"/paper/pastanet-toward-human-activity-knowledge","slug":"pastanet-toward-human-activity-knowledge","title":"PaStaNet: Toward Human Activity Knowledge Engine","date":"2020-04-02","arxiv_id":"2004.00945","repositories_listed":2,"syntology":null},{"url":"/paper/harvesting-ambient-rf-for-presence-detection","slug":"harvesting-ambient-rf-for-presence-detection","title":"Harvesting Ambient RF for Presence Detection Through Deep Learning","date":"2020-02-13","arxiv_id":"2002.05770","repositories_listed":2,"syntology":null},{"url":"/paper/actions-as-moving-points","slug":"actions-as-moving-points","title":"Actions as Moving Points","date":"2020-01-14","arxiv_id":"2001.04608","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/actions-as-moving-points#ran","syntology_url":"https://syntology.ai/paper/2001.04608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04608"}},"official":{"repos":["MCG-NJU/MOC-Detector"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-moments-in-time-learning-and","slug":"multi-moments-in-time-learning-and","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","date":"2019-11-01","arxiv_id":"1911.00232","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-moments-in-time-learning-and#ran","syntology_url":"https://syntology.ai/paper/1911.00232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00232"}},"official":null}},{"url":"/paper/personal-vad-speaker-conditioned-voice","slug":"personal-vad-speaker-conditioned-voice","title":"Personal VAD: Speaker-Conditioned Voice Activity Detection","date":"2019-08-12","arxiv_id":"1908.04284","repositories_listed":2,"syntology":null},{"url":"/paper/actor-conditioned-attention-maps-for-video","slug":"actor-conditioned-attention-maps-for-video","title":"Actor Conditioned Attention Maps for Video Action Detection","date":"2018-12-30","arxiv_id":"1812.11631","repositories_listed":2,"syntology":null},{"url":"/paper/soccernet-a-scalable-dataset-for-action","slug":"soccernet-a-scalable-dataset-for-action","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","date":"2018-04-12","arxiv_id":"1804.04527","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/soccernet-a-scalable-dataset-for-action#ran","syntology_url":"https://syntology.ai/paper/1804.04527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.04527"}},"official":null}},{"url":"/paper/rethinking-spatiotemporal-feature-learning","slug":"rethinking-spatiotemporal-feature-learning","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","date":"2017-12-13","arxiv_id":"1712.04851","repositories_listed":2,"syntology":null},{"url":"/paper/learning-latent-super-events-to-detect","slug":"learning-latent-super-events-to-detect","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","date":"2017-12-05","arxiv_id":"1712.01938","repositories_listed":2,"syntology":null},{"url":"/paper/single-shot-temporal-action-detection","slug":"single-shot-temporal-action-detection","title":"Single Shot Temporal Action Detection","date":"2017-10-17","arxiv_id":"1710.06236","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/single-shot-temporal-action-detection#ran","syntology_url":"https://syntology.ai/paper/1710.06236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.06236"}},"official":null}},{"url":"/paper/speaker-diarization-with-overlapping","slug":"speaker-diarization-with-overlapping","title":"Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm","date":"2025-06-03","arxiv_id":"2506.02610","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10879","slug":"2505-10879","title":"Multi-Stage Speaker Diarization for Noisy Classrooms","date":"2025-05-16","arxiv_id":"2505.10879","repositories_listed":1,"syntology":null},{"url":"/paper/digit-multi-dilated-gated-encoder-and-central","slug":"digit-multi-dilated-gated-encoder-and-central","title":"DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer","date":"2025-05-09","arxiv_id":"2505.05711","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-open-vocabulary-action-detection","slug":"scaling-open-vocabulary-action-detection","title":"Scaling Open-Vocabulary Action Detection","date":"2025-04-04","arxiv_id":"2504.03096","repositories_listed":1,"syntology":null},{"url":"/paper/context-enhanced-memory-refined-transformer","slug":"context-enhanced-memory-refined-transformer","title":"Context-Enhanced Memory-Refined Transformer for Online Action Detection","date":"2025-03-24","arxiv_id":"2503.18359","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-large-language-models-for-esg","slug":"optimizing-large-language-models-for-esg","title":"Optimizing Large Language Models for ESG Activity Detection in Financial Texts","date":"2025-02-28","arxiv_id":"2502.21112","repositories_listed":1,"syntology":null},{"url":"/paper/opentad-a-unified-framework-and-comprehensive","slug":"opentad-a-unified-framework-and-comprehensive","title":"OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection","date":"2025-02-27","arxiv_id":"2502.20361","repositories_listed":1,"syntology":null},{"url":"/paper/vanpy-voice-analysis-framework","slug":"vanpy-voice-analysis-framework","title":"VANPY: Voice Analysis Framework","date":"2025-02-17","arxiv_id":"2502.17579","repositories_listed":1,"syntology":null},{"url":"/paper/when-do-they-stop-a-first-step-towards","slug":"when-do-they-stop-a-first-step-towards","title":"When do they StOP?: A First Step Towards Automatically Identifying Team Communication in the Operating Room","date":"2025-02-12","arxiv_id":"2502.08299","repositories_listed":1,"syntology":null},{"url":"/paper/pre-equalization-aided-grant-free-massive","slug":"pre-equalization-aided-grant-free-massive","title":"Pre-Equalization Aided Grant-Free Massive Access in Massive MIMO System","date":"2025-02-10","arxiv_id":"2502.06239","repositories_listed":1,"syntology":null},{"url":"/paper/preventing-rogue-agents-improves-multi-agent","slug":"preventing-rogue-agents-improves-multi-agent","title":"Preventing Rogue Agents Improves Multi-Agent Collaboration","date":"2025-02-09","arxiv_id":"2502.05986","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-detection-and-prediction-of-namd","slug":"automatic-detection-and-prediction-of-namd","title":"Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality","date":"2025-01-24","arxiv_id":"2501.14323","repositories_listed":1,"syntology":null},{"url":"/paper/text-driven-online-action-detection","slug":"text-driven-online-action-detection","title":"Text-driven Online Action Detection","date":"2025-01-23","arxiv_id":"2501.13518","repositories_listed":1,"syntology":null},{"url":"/paper/training-free-zero-shot-temporal-action","slug":"training-free-zero-shot-temporal-action","title":"Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models","date":"2025-01-23","arxiv_id":"2501.13795","repositories_listed":1,"syntology":null},{"url":"/paper/ms-temba-multi-scale-temporal-mamba-for","slug":"ms-temba-multi-scale-temporal-mamba-for","title":"MS-Temba : Multi-Scale Temporal Mamba for Efficient Temporal Action Detection","date":"2025-01-10","arxiv_id":"2501.06138","repositories_listed":1,"syntology":null},{"url":"/paper/action-agnostic-point-level-supervision-for","slug":"action-agnostic-point-level-supervision-for","title":"Action-Agnostic Point-Level Supervision for Temporal Action Detection","date":"2024-12-30","arxiv_id":"2412.21205","repositories_listed":1,"syntology":null},{"url":"/paper/wifi-csi-based-temporal-activity-detection","slug":"wifi-csi-based-temporal-activity-detection","title":"WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network","date":"2024-12-19","arxiv_id":"2412.16233","repositories_listed":1,"syntology":null},{"url":"/paper/jovale-detecting-human-actions-in-video-using","slug":"jovale-detecting-human-actions-in-video-using","title":"JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts","date":"2024-12-18","arxiv_id":"2412.13708","repositories_listed":1,"syntology":null},{"url":"/paper/usdrl-unified-skeleton-based-dense","slug":"usdrl-unified-skeleton-based-dense","title":"USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation","date":"2024-12-12","arxiv_id":"2412.09220","repositories_listed":1,"syntology":null},{"url":"/paper/automating-feedback-analysis-in-surgical","slug":"automating-feedback-analysis-in-surgical","title":"Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment","date":"2024-12-01","arxiv_id":"2412.00760","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-vlm-localizability-and-semantics","slug":"exploiting-vlm-localizability-and-semantics","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","date":"2024-11-17","arxiv_id":"2411.10922","repositories_listed":1,"syntology":null},{"url":"/paper/on-occlusions-in-video-action-detection-1","slug":"on-occlusions-in-video-action-detection-1","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","date":"2024-10-25","arxiv_id":"2410.19553","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-occlusions-in-video-action-detection-1#ran","syntology_url":"https://syntology.ai/paper/2410.19553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19553"}},"official":{"repos":["rajatmodi62/occludedactionbenchmark"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-framework-for-adapting-human-robot","slug":"a-framework-for-adapting-human-robot","title":"A Framework for Adapting Human-Robot Interaction to Diverse User Groups","date":"2024-10-15","arxiv_id":"2410.11377","repositories_listed":1,"syntology":null},{"url":"/paper/cefdet-cognitive-effectiveness-network-based","slug":"cefdet-cognitive-effectiveness-network-based","title":"Cefdet: Cognitive Effectiveness Network Based on Fuzzy Inference for Action Detection","date":"2024-10-08","arxiv_id":"2410.05771","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-guided-appearance-motion","slug":"uncertainty-guided-appearance-motion","title":"Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection","date":"2024-09-16","arxiv_id":"2409.09953","repositories_listed":1,"syntology":null},{"url":"/paper/towards-student-actions-in-classroom-scenes","slug":"towards-student-actions-in-classroom-scenes","title":"Towards Student Actions in Classroom Scenes: New Dataset and Baseline","date":"2024-09-02","arxiv_id":"2409.00926","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02623","slug":"2408-02623","title":"YOWOv3: An Efficient and Generalized Framework for Human Action Detection and Recognition","date":"2024-08-05","arxiv_id":"2408.02623","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-temporal-causality-for-advanced","slug":"harnessing-temporal-causality-for-advanced","title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","date":"2024-07-25","arxiv_id":"2407.17792","repositories_listed":1,"syntology":null},{"url":"/paper/marine-a-computer-vision-model-for-detecting","slug":"marine-a-computer-vision-model-for-detecting","title":"MARINE: A Computer Vision Model for Detecting Rare Predator-Prey Interactions in Animal Videos","date":"2024-07-25","arxiv_id":"2407.18289","repositories_listed":1,"syntology":null},{"url":"/paper/actionswitch-class-agnostic-detection-of","slug":"actionswitch-class-agnostic-detection-of","title":"ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos","date":"2024-07-17","arxiv_id":"2407.12987","repositories_listed":1,"syntology":null},{"url":"/paper/mmad-multi-label-micro-action-detection-in","slug":"mmad-multi-label-micro-action-detection-in","title":"MMAD: Multi-label Micro-Action Detection in Videos","date":"2024-07-07","arxiv_id":"2407.05311","repositories_listed":1,"syntology":null},{"url":"/paper/dyfadet-dynamic-feature-aggregation-for","slug":"dyfadet-dynamic-feature-aggregation-for","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","date":"2024-07-03","arxiv_id":"2407.03197","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":4,"n_instrument":8,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"12 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; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dyfadet-dynamic-feature-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2407.03197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03197"}},"official":{"repos":["yangle15/DyFADet-pytorch"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-deep-learning-models-on-nvidia","slug":"benchmarking-deep-learning-models-on-nvidia","title":"Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation","date":"2024-06-25","arxiv_id":"2406.17749","repositories_listed":1,"syntology":null},{"url":"/paper/inagvad-a-challenging-french-tv-and-radio","slug":"inagvad-a-challenging-french-tv-and-radio","title":"InaGVAD : a Challenging French TV and Radio Corpus Annotated for Speech Activity Detection and Speaker Gender Segmentation","date":"2024-06-06","arxiv_id":"2406.04429","repositories_listed":1,"syntology":null},{"url":"/paper/one-stage-open-vocabulary-temporal-action","slug":"one-stage-open-vocabulary-temporal-action","title":"One-Stage Open-Vocabulary Temporal Action Detection Leveraging Temporal Multi-scale and Action Label Features","date":"2024-04-30","arxiv_id":"2404.19542","repositories_listed":1,"syntology":null},{"url":"/paper/tim-a-time-interval-machine-for-audio-visual","slug":"tim-a-time-interval-machine-for-audio-visual","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","date":"2024-04-08","arxiv_id":"2404.05559","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":0,"n_honours":5,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tim-a-time-interval-machine-for-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2404.05559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05559"}},"official":{"repos":["jacobchalk/tim"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unimd-towards-unifying-moment-retrieval-and","slug":"unimd-towards-unifying-moment-retrieval-and","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","date":"2024-04-07","arxiv_id":"2404.04933","repositories_listed":1,"syntology":null},{"url":"/paper/te-tad-towards-full-end-to-end-temporal","slug":"te-tad-towards-full-end-to-end-temporal","title":"TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression","date":"2024-04-03","arxiv_id":"2404.02405","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-the-robustness-of-temporal","slug":"benchmarking-the-robustness-of-temporal","title":"Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions","date":"2024-03-29","arxiv_id":"2403.20254","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/benchmarking-the-robustness-of-temporal#ran","syntology_url":"https://syntology.ai/paper/2403.20254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20254"}},"official":{"repos":["alvin-zeng/temporal-robustness-benchmark"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/online-speaker-diarization-of-meetings-guided","slug":"online-speaker-diarization-of-meetings-guided","title":"Online speaker diarization of meetings guided by speech separation","date":"2024-01-30","arxiv_id":"2402.00067","repositories_listed":1,"syntology":null},{"url":"/paper/glance-and-focus-memory-prompting-for-multi-1","slug":"glance-and-focus-memory-prompting-for-multi-1","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","date":"2024-01-03","arxiv_id":"2401.01529","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":2,"n_ran_checked":6,"n_instrument":8,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/glance-and-focus-memory-prompting-for-multi-1#ran","syntology_url":"https://syntology.ai/paper/2401.01529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01529"}},"official":{"repos":["byz0e/glance-focus"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/sada-semantic-adversarial-unsupervised-domain","slug":"sada-semantic-adversarial-unsupervised-domain","title":"SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization","date":"2023-12-20","arxiv_id":"2312.13377","repositories_listed":1,"syntology":null},{"url":"/paper/generative-model-based-feature-knowledge","slug":"generative-model-based-feature-knowledge","title":"Generative Model-based Feature Knowledge Distillation for Action Recognition","date":"2023-12-14","arxiv_id":"2312.08644","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-active-learning-for-video","slug":"semi-supervised-active-learning-for-video","title":"Semi-supervised Active Learning for Video Action Detection","date":"2023-12-12","arxiv_id":"2312.07169","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/semi-supervised-active-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2312.07169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07169"}},"official":{"repos":["akash2907/semi-sup-active-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}}],"syntology_records":31,"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":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_where_code_ran":53,"papers_where_code_ran_first_page":"/task/action-detection/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":9,"url":"/task/action-detection/papers/2","json":"/task/action-detection/papers/2.json","rows":100},{"order":"archive","page":3,"of":9,"url":"/task/action-detection/papers/3","json":"/task/action-detection/papers/3.json","rows":100},{"order":"archive","page":4,"of":9,"url":"/task/action-detection/papers/4","json":"/task/action-detection/papers/4.json","rows":100},{"order":"archive","page":5,"of":9,"url":"/task/action-detection/papers/5","json":"/task/action-detection/papers/5.json","rows":100},{"order":"archive","page":6,"of":9,"url":"/task/action-detection/papers/6","json":"/task/action-detection/papers/6.json","rows":100},{"order":"archive","page":7,"of":9,"url":"/task/action-detection/papers/7","json":"/task/action-detection/papers/7.json","rows":100},{"order":"archive","page":8,"of":9,"url":"/task/action-detection/papers/8","json":"/task/action-detection/papers/8.json","rows":100},{"order":"archive","page":9,"of":9,"url":"/task/action-detection/papers/9","json":"/task/action-detection/papers/9.json","rows":17},{"order":"ran","page":1,"of":1,"url":"/task/action-detection/papers/ran/1","json":"/task/action-detection/papers/ran/1.json","rows":53}],"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":"3c44a4d139c14fd5bf2a3f7307b30454237257a9adce813e14b4481d029748d7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}