{"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-recognition","name":"Temporal Action Localization","slug":"action-recognition","description_markdown":"Temporal Action Localization aims to detect activities in the video stream and  output beginning and end timestamps. It is closely related to  Temporal Action Proposal Generation.","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":1477,"papers_with_code":493,"benchmarks":14,"benchmark_tables_in_archive":14,"benchmark_tables_shown":14,"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":42,"subtasks":8,"parent_tasks":3},"benchmarks":[{"leaderboard":"/sota/temporal-action-localization-on-thumos14","slug":"temporal-action-localization-on-thumos14","dataset":"THUMOS’14","dataset_url":"/dataset/thumos14-1","rows_in_archive":42,"metrics":["Avg mAP (0.3:0.7)","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5","mAP IOU@0.6","mAP IOU@0.7"],"first_row_in_archive_order":{"model":"AdaTAD (VideoMAEv2-giant)","paper_title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","paper_url":"/paper/end-to-end-temporal-action-detection-with-1b","paper_date":"2023-11-28","arxiv_id":"2311.17241","code_links":[{"title":"sming256/OpenTAD","url":"https://github.com/sming256/OpenTAD"},{"title":"sming256/AdaTAD","url":"https://github.com/sming256/AdaTAD"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-activitynet","slug":"temporal-action-localization-on-activitynet","dataset":"ActivityNet-1.3","dataset_url":"/dataset/activitynet","rows_in_archive":33,"metrics":["mAP","mAP IOU@0.5","mAP IOU@0.75","mAP IOU@0.95"],"first_row_in_archive_order":{"model":"RDFA-S6 (InternVideo2-6B)","paper_title":"Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism","paper_url":"/paper/enhancing-temporal-action-localization","paper_date":"2024-07-18","arxiv_id":"2407.13078","code_links":[{"title":"lsy0882/RDFA-S6","url":"https://github.com/lsy0882/RDFA-S6"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-hacs","slug":"temporal-action-localization-on-hacs","dataset":"HACS","dataset_url":"/dataset/hacs","rows_in_archive":12,"metrics":["Average-mAP","mAP@0.5","mAP@0.75","mAP@0.95"],"first_row_in_archive_order":{"model":"RDFA-S6 (InternVideo2-6B)","paper_title":"Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism","paper_url":"/paper/enhancing-temporal-action-localization","paper_date":"2024-07-18","arxiv_id":"2407.13078","code_links":[{"title":"lsy0882/RDFA-S6","url":"https://github.com/lsy0882/RDFA-S6"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-fineaction","slug":"temporal-action-localization-on-fineaction","dataset":"FineAction","dataset_url":"/dataset/fineaction","rows_in_archive":9,"metrics":["mAP","mAP IOU@0.5","mAP IOU@0.75","mAP IOU@0.95"],"first_row_in_archive_order":{"model":"RDFA-S6 (InternVideo2-6B)","paper_title":"Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism","paper_url":"/paper/enhancing-temporal-action-localization","paper_date":"2024-07-18","arxiv_id":"2407.13078","code_links":[{"title":"lsy0882/RDFA-S6","url":"https://github.com/lsy0882/RDFA-S6"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-multithumos-1","slug":"temporal-action-localization-on-multithumos-1","dataset":"MultiTHUMOS","dataset_url":"/dataset/multithumos","rows_in_archive":8,"metrics":["Average mAP","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5","mAP IOU@0.6","mAP IOU@0.7","mAP IOU@0.8","mAP IOU@0.9"],"first_row_in_archive_order":{"model":"TriDet (VideoMAEv2)","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","paper_url":"/paper/temporal-action-localization-with-enhanced","paper_date":"2023-09-11","arxiv_id":"2309.05590","code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-crosstask","slug":"temporal-action-localization-on-crosstask","dataset":"CrossTask","dataset_url":"/dataset/crosstask","rows_in_archive":7,"metrics":["Recall"],"first_row_in_archive_order":{"model":"VideoCLIP","paper_title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","paper_url":"/paper/videoclip-contrastive-pre-training-for-zero","paper_date":"2021-09-28","arxiv_id":"2109.14084","code_links":[{"title":"facebookresearch/fairseq","url":"https://github.com/facebookresearch/fairseq"},{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-epic-kitchens","slug":"temporal-action-localization-on-epic-kitchens","dataset":"EPIC-KITCHENS-100","dataset_url":"/dataset/epic-kitchens-100","rows_in_archive":6,"metrics":["Avg mAP (0.1-0.5)","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5"],"first_row_in_archive_order":{"model":"AdaTAD (verb, VideoMAE-L)","paper_title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","paper_url":"/paper/end-to-end-temporal-action-detection-with-1b","paper_date":"2023-11-28","arxiv_id":"2311.17241","code_links":[{"title":"sming256/OpenTAD","url":"https://github.com/sming256/OpenTAD"},{"title":"sming256/AdaTAD","url":"https://github.com/sming256/AdaTAD"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-muses","slug":"temporal-action-localization-on-muses","dataset":"MUSES","dataset_url":"/dataset/muses","rows_in_archive":2,"metrics":["mAP","mAP@0.3","mAP@0.4","mAP@0.5","mAP@0.6","mAP@0.7"],"first_row_in_archive_order":{"model":"TemporalMaxer","paper_title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","paper_url":"/paper/temporalmaxer-maximize-temporal-context-with","paper_date":"2023-03-16","arxiv_id":"2303.09055","code_links":[{"title":"tuantng/temporalmaxer","url":"https://github.com/tuantng/temporalmaxer"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-activitynet-1","slug":"temporal-action-localization-on-activitynet-1","dataset":"ActivityNet-1.2","dataset_url":"/dataset/activitynet","rows_in_archive":1,"metrics":["mAP IOU@0.5","mAP IOU@0.1","mAP IOU@0.3","mAP IOU@0.7"],"first_row_in_archive_order":{"model":"DeepMetricLearner","paper_title":"Weakly Supervised Temporal Action Localization Using Deep Metric Learning","paper_url":"/paper/weakly-supervised-temporal-action-1","paper_date":"2020-01-21","arxiv_id":"2001.07793","code_links":[{"title":"asrafulashiq/wsad","url":"https://github.com/asrafulashiq/wsad"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-ego4d-mq-test","slug":"temporal-action-localization-on-ego4d-mq-test","dataset":"Ego4D MQ test","dataset_url":"/dataset/ego4d","rows_in_archive":1,"metrics":["Average mAP","Recall@1x (tIoU=0.5)"],"first_row_in_archive_order":{"model":"ActionFormer (SlowFast+Omnivore+EgoVLP)","paper_title":"Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge","paper_url":"/paper/where-a-strong-backbone-meets-strong-features","paper_date":"2022-11-16","arxiv_id":"2211.09074","code_links":[{"title":"happyharrycn/actionformer_release","url":"https://github.com/happyharrycn/actionformer_release"},{"title":"showlab/egovlp","url":"https://github.com/showlab/egovlp"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-ego4d-mq-val","slug":"temporal-action-localization-on-ego4d-mq-val","dataset":"Ego4D MQ val","dataset_url":"/dataset/ego4d","rows_in_archive":1,"metrics":["Average mAP","Recall@1x (tIoU=0.5)"],"first_row_in_archive_order":{"model":"ActionFormer (SlowFast+Omnivore+EgoVLP)","paper_title":"Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge","paper_url":"/paper/where-a-strong-backbone-meets-strong-features","paper_date":"2022-11-16","arxiv_id":"2211.09074","code_links":[{"title":"happyharrycn/actionformer_release","url":"https://github.com/happyharrycn/actionformer_release"},{"title":"showlab/egovlp","url":"https://github.com/showlab/egovlp"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-mexaction2","slug":"temporal-action-localization-on-mexaction2","dataset":"MEXaction2","dataset_url":null,"rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"S-CNN","paper_title":"Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs","paper_url":"/paper/temporal-action-localization-in-untrimmed","paper_date":"2016-01-09","arxiv_id":"1601.02129","code_links":[{"title":"zhengshou/scnn","url":"https://github.com/zhengshou/scnn"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-thumos-14","slug":"temporal-action-localization-on-thumos-14","dataset":"THUMOS'14","dataset_url":"/dataset/thumos14-1","rows_in_archive":1,"metrics":["mAP IOU@0.5"],"first_row_in_archive_order":{"model":"AVFusion","paper_title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","paper_url":"/paper/hear-me-out-fusional-approaches-for-audio","paper_date":"2021-06-27","arxiv_id":"2106.14118","code_links":[{"title":"skelemoa/tal-hmo","url":"https://github.com/skelemoa/tal-hmo"}],"syntology":null}},{"leaderboard":"/sota/temporal-action-localization-on-thumos14-2","slug":"temporal-action-localization-on-thumos14-2","dataset":"THUMOS14","dataset_url":"/dataset/thumos14-1","rows_in_archive":1,"metrics":["Avg mAP (0.3:0.7)"],"first_row_in_archive_order":{"model":"BasicTAD (R50-SlowOnly)","paper_title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","paper_url":"/paper/basictad-an-astounding-rgb-only-baseline-for","paper_date":"2022-05-05","arxiv_id":"2205.02717","code_links":[{"title":"mcg-nju/basictad","url":"https://github.com/mcg-nju/basictad"},{"title":"cg1177/dcan","url":"https://github.com/cg1177/dcan"}],"syntology":null}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/hmdb51","name":"HMDB51","full_name":"","num_papers_in_archive":839},{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/mpii","name":"MPII","full_name":"MPII Human Pose","num_papers_in_archive":495},{"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/kth","name":"KTH","full_name":"KTH Action dataset","num_papers_in_archive":279},{"url":"/dataset/epic-kitchens-100","name":"EPIC-KITCHENS-100","full_name":"","num_papers_in_archive":162},{"url":"/dataset/coin","name":"COIN","full_name":"","num_papers_in_archive":105},{"url":"/dataset/kinetics-700","name":"Kinetics-700","full_name":"Kinetics-700","num_papers_in_archive":95},{"url":"/dataset/finegym","name":"FineGym","full_name":"FineGym","num_papers_in_archive":76},{"url":"/dataset/hacs","name":"HACS","full_name":"Human Action Clips and Segments","num_papers_in_archive":75},{"url":"/dataset/babel-1","name":"BABEL","full_name":"","num_papers_in_archive":72},{"url":"/dataset/utd-mhad","name":"UTD-MHAD","full_name":"","num_papers_in_archive":62},{"url":"/dataset/multithumos","name":"MultiTHUMOS","full_name":"","num_papers_in_archive":58},{"url":"/dataset/crosstask","name":"CrossTask","full_name":"CrossTask","num_papers_in_archive":54},{"url":"/dataset/ego4d","name":"Ego4D","full_name":"","num_papers_in_archive":32},{"url":"/dataset/ikea-asm","name":"IKEA ASM","full_name":"","num_papers_in_archive":25},{"url":"/dataset/fineaction","name":"FineAction","full_name":"","num_papers_in_archive":24},{"url":"/dataset/hieve","name":"HiEve","full_name":"Human-in-Events","num_papers_in_archive":19},{"url":"/dataset/florence3d","name":"Florence3D","full_name":"","num_papers_in_archive":18},{"url":"/dataset/hvu","name":"HVU","full_name":"Holistic Video Understanding","num_papers_in_archive":16},{"url":"/dataset/muses","name":"MUSES","full_name":"MUlti-Shot EventS","num_papers_in_archive":12},{"url":"/dataset/perception-test","name":"Perception Test","full_name":"","num_papers_in_archive":10},{"url":"/dataset/eyth","name":"EYTH","full_name":"EgoYouTubeHands","num_papers_in_archive":7},{"url":"/dataset/msr-actionpairs","name":"MSR ActionPairs","full_name":"","num_papers_in_archive":7},{"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/wear","name":"WEAR","full_name":"WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition","num_papers_in_archive":5},{"url":"/dataset/tinyvirat","name":"TinyVIRAT","full_name":"","num_papers_in_archive":4},{"url":"/dataset/composable-activities-dataset","name":"Composable activities dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/converse","name":"CONVERSE","full_name":"","num_papers_in_archive":3},{"url":"/dataset/decade","name":"DECADE","full_name":"","num_papers_in_archive":3},{"url":"/dataset/hollywood-3d-dataset","name":"Hollywood 3D dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/oreba","name":"OREBA","full_name":"Objectively Recognizing Eating Behavior and Associated Intake","num_papers_in_archive":3},{"url":"/dataset/uav-gesture","name":"UAV-GESTURE","full_name":"","num_papers_in_archive":3},{"url":"/dataset/mcad","name":"MCAD","full_name":"Multi-Camera Action Dataset","num_papers_in_archive":2},{"url":"/dataset/rise","name":"RISE","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/skeletics-152-1","name":"Skeletics 152","full_name":"","num_papers_in_archive":2},{"url":"/dataset/metaphorics","name":"Metaphorics","full_name":"","num_papers_in_archive":1},{"url":"/dataset/whenact","name":"WhenAct","full_name":"Temporal Human Action Localization in Lifestyle Vlogs","num_papers_in_archive":1}],"subtasks":[{"url":"/task/3d-human-action-recognition","name":"3D Action Recognition"},{"url":"/task/action-recognition-in-still-images","name":"Action Recognition In Still Images"},{"url":"/task/activity-recognition-in-videos","name":"Activity Recognition In Videos"},{"url":"/task/open-vocab-temporal-action-detection","name":"Open-vocab Temporal Action Detection"},{"url":"/task/temporal-action-proposal-generation","name":"Temporal Action Proposal Generation"},{"url":"/task/temporal-group-activity-localization","name":"Temporal Group Activity Localization"},{"url":"/task/weakly-supervised-action-localization","name":"Weakly Supervised Action Localization"},{"url":"/task/weakly-supervised-temporal-action","name":"Weakly-supervised Temporal Action Localization"}],"parent_tasks":[{"url":"/task/action-localization","name":"Action Localization"},{"url":"/task/video","name":"Video"},{"url":"/task/zero-shot-learning","name":"Zero-Shot Learning"}],"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":15,"rows_per_page":100,"shown":100,"of":1477,"of_with_code":493,"tagged_in_all":1477,"counts":{"archive_papers_tagged":1477,"with_a_code_link":493,"where_syntology_ran_a_sample":87,"not_listed_spam_title":0,"listed":1477,"listed_where_code_ran":87,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":66,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":66,"listed_every_run_a_failure_of_syntologys_instrument":21,"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/spatial-temporal-graph-convolutional-networks-1","slug":"spatial-temporal-graph-convolutional-networks-1","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2018-01-23","arxiv_id":"1801.07455","repositories_listed":24,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatial-temporal-graph-convolutional-networks-1#ran","syntology_url":"https://syntology.ai/paper/1801.07455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.07455"}},"official":{"repos":["yysijie/st-gcn"],"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/a-closer-look-at-spatiotemporal-convolutions","slug":"a-closer-look-at-spatiotemporal-convolutions","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","date":"2017-11-30","arxiv_id":"1711.11248","repositories_listed":24,"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":4,"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/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}},"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/grad-cam-improved-visual-explanations-for","slug":"grad-cam-improved-visual-explanations-for","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","date":"2017-10-30","arxiv_id":"1710.11063","repositories_listed":24,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/grad-cam-improved-visual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/1710.11063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11063"}},"official":{"repos":["adityac94/Grad_CAM_plus_plus"],"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/temporal-segment-networks-towards-good","slug":"temporal-segment-networks-towards-good","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","date":"2016-08-02","arxiv_id":"1608.00859","repositories_listed":22,"syntology":{"n":24,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":14,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"10 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; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/temporal-segment-networks-towards-good#ran","syntology_url":"https://syntology.ai/paper/1608.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.00859"}},"official":{"repos":["yjxiong/caffe","yjxiong/temporal-segment-networks"],"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/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/unsupervised-learning-of-video","slug":"unsupervised-learning-of-video","title":"Unsupervised Learning of Video Representations using LSTMs","date":"2015-02-16","arxiv_id":"1502.04681","repositories_listed":12,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-learning-of-video#ran","syntology_url":"https://syntology.ai/paper/1502.04681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.04681"}},"official":{"repos":["emansim/unsupervised-videos"],"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":["listed","official"]}}},{"url":"/paper/temporal-segment-networks-for-action","slug":"temporal-segment-networks-for-action","title":"Temporal Segment Networks for Action Recognition in Videos","date":"2017-05-08","arxiv_id":"1705.02953","repositories_listed":11,"syntology":null},{"url":"/paper/graph-based-global-reasoning-networks","slug":"graph-based-global-reasoning-networks","title":"Graph-Based Global Reasoning Networks","date":"2018-11-30","arxiv_id":"1811.12814","repositories_listed":9,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":7,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"15 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; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/graph-based-global-reasoning-networks#ran","syntology_url":"https://syntology.ai/paper/1811.12814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12814"}},"official":{"repos":["facebookresearch/GloRe"],"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/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/stnet-local-and-global-spatial-temporal","slug":"stnet-local-and-global-spatial-temporal","title":"StNet: Local and Global Spatial-Temporal Modeling for Action Recognition","date":"2018-11-05","arxiv_id":"1811.01549","repositories_listed":8,"syntology":null},{"url":"/paper/g-tad-sub-graph-localization-for-temporal","slug":"g-tad-sub-graph-localization-for-temporal","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","date":"2019-11-26","arxiv_id":"1911.11462","repositories_listed":7,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/g-tad-sub-graph-localization-for-temporal#ran","syntology_url":"https://syntology.ai/paper/1911.11462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.11462"}},"official":{"repos":["Frostinassiky/gtad"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multivariate-lstm-fcns-for-time-series","slug":"multivariate-lstm-fcns-for-time-series","title":"Multivariate LSTM-FCNs for Time Series Classification","date":"2018-01-14","arxiv_id":"1801.04503","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/multivariate-lstm-fcns-for-time-series#ran","syntology_url":"https://syntology.ai/paper/1801.04503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.04503"}},"official":{"repos":["houshd/MLSTM-FCN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/two-stream-convolutional-networks-for-action","slug":"two-stream-convolutional-networks-for-action","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","date":"2014-06-09","arxiv_id":"1406.2199","repositories_listed":7,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 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) · 2 unverified","sample_list":"/paper/two-stream-convolutional-networks-for-action#ran","syntology_url":"https://syntology.ai/paper/1406.2199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1406.2199"}},"official":{"repos":["feichtenhofer/twostreamfusion"],"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/ucf101-a-dataset-of-101-human-actions-classes","slug":"ucf101-a-dataset-of-101-human-actions-classes","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","date":"2012-12-03","arxiv_id":"1212.0402","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/ucf101-a-dataset-of-101-human-actions-classes#ran","syntology_url":"https://syntology.ai/paper/1212.0402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1212.0402"}},"official":null}},{"url":"/paper/eva-exploring-the-limits-of-masked-visual","slug":"eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","arxiv_id":"2211.07636","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}},"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/co-occurrence-feature-learning-from-skeleton","slug":"co-occurrence-feature-learning-from-skeleton","title":"Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation","date":"2018-04-17","arxiv_id":"1804.06055","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/co-occurrence-feature-learning-from-skeleton#ran","syntology_url":"https://syntology.ai/paper/1804.06055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.06055"}},"official":{"repos":["hikvision-research/skelact"],"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":["listed","official"]}}},{"url":"/paper/delving-deeper-into-convolutional-networks","slug":"delving-deeper-into-convolutional-networks","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","date":"2015-11-19","arxiv_id":"1511.06432","repositories_listed":6,"syntology":null},{"url":"/paper/acgnet-action-complement-graph-network-for","slug":"acgnet-action-complement-graph-network-for","title":"ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization","date":"2021-12-21","arxiv_id":"2112.10977","repositories_listed":5,"syntology":null},{"url":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 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) · 3 unverified","sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}},"official":{"repos":["google-research/google-research"],"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/what-and-how-well-you-performed-a-multitask","slug":"what-and-how-well-you-performed-a-multitask","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","date":"2019-04-08","arxiv_id":"1904.04346","repositories_listed":5,"syntology":null},{"url":"/paper/representation-flow-for-action-recognition","slug":"representation-flow-for-action-recognition","title":"Representation Flow for Action Recognition","date":"2018-10-02","arxiv_id":"1810.01455","repositories_listed":5,"syntology":null},{"url":"/paper/ridiculously-fast-shot-boundary-detection","slug":"ridiculously-fast-shot-boundary-detection","title":"Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks","date":"2017-05-23","arxiv_id":"1705.08214","repositories_listed":5,"syntology":null},{"url":"/paper/towards-good-practices-for-very-deep-two","slug":"towards-good-practices-for-very-deep-two","title":"Towards Good Practices for Very Deep Two-Stream ConvNets","date":"2015-07-08","arxiv_id":"1507.02159","repositories_listed":5,"syntology":null},{"url":"/paper/describing-videos-by-exploiting-temporal","slug":"describing-videos-by-exploiting-temporal","title":"Describing Videos by Exploiting Temporal Structure","date":"2015-02-27","arxiv_id":"1502.08029","repositories_listed":5,"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/describing-videos-by-exploiting-temporal#ran","syntology_url":"https://syntology.ai/paper/1502.08029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.08029"}},"official":{"repos":["yaoli/arctic-capgen-vid"],"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/action-transformer-a-self-attention-model-for","slug":"action-transformer-a-self-attention-model-for","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","date":"2021-07-01","arxiv_id":"2107.00606","repositories_listed":4,"syntology":null},{"url":"/paper/non-local-graph-convolutional-networks-for","slug":"non-local-graph-convolutional-networks-for","title":"Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2018-05-20","arxiv_id":"1805.07694","repositories_listed":4,"syntology":null},{"url":"/paper/moments-in-time-dataset-one-million-videos","slug":"moments-in-time-dataset-one-million-videos","title":"Moments in Time Dataset: one million videos for event understanding","date":"2018-01-09","arxiv_id":"1801.03150","repositories_listed":4,"syntology":null},{"url":"/paper/im2flow-motion-hallucination-from-static","slug":"im2flow-motion-hallucination-from-static","title":"Im2Flow: Motion Hallucination from Static Images for Action Recognition","date":"2017-12-12","arxiv_id":"1712.04109","repositories_listed":4,"syntology":null},{"url":"/paper/ts-lstm-and-temporal-inception-exploiting","slug":"ts-lstm-and-temporal-inception-exploiting","title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","date":"2017-03-30","arxiv_id":"1703.10667","repositories_listed":4,"syntology":null},{"url":"/paper/explaining-nonlinear-classification-decisions","slug":"explaining-nonlinear-classification-decisions","title":"Explaining NonLinear Classification Decisions with Deep Taylor Decomposition","date":"2015-12-08","arxiv_id":"1512.02479","repositories_listed":4,"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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/explaining-nonlinear-classification-decisions#ran","syntology_url":"https://syntology.ai/paper/1512.02479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.02479"}},"official":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/video-focalnets-spatio-temporal-focal","slug":"video-focalnets-spatio-temporal-focal","title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition","date":"2023-07-13","arxiv_id":"2307.06947","repositories_listed":3,"syntology":{"n":32,"n_ran":23,"n_constructed":7,"n_ran_checked":16,"n_instrument":7,"n_unverified":9,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":21,"phrase":"23 ran (of which 7 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/video-focalnets-spatio-temporal-focal#ran","syntology_url":"https://syntology.ai/paper/2307.06947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06947"}},"official":{"repos":["talalwasim/video-focalnets"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/movinets-mobile-video-networks-for-efficient","slug":"movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","arxiv_id":"2103.11511","repositories_listed":3,"syntology":{"n":13,"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}},"official":{"repos":["tensorflow/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/mvfnet-multi-view-fusion-network-for","slug":"mvfnet-multi-view-fusion-network-for","title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","date":"2020-12-13","arxiv_id":"2012.06977","repositories_listed":3,"syntology":null},{"url":"/paper/lifelong-graph-learning","slug":"lifelong-graph-learning","title":"Lifelong Graph Learning","date":"2020-09-01","arxiv_id":"2009.00647","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lifelong-graph-learning#ran","syntology_url":"https://syntology.ai/paper/2009.00647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.00647"}},"official":{"repos":["wang-chen/LGL","wang-chen/lgl-action-recognition"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/richly-activated-graph-convolutional-network","slug":"richly-activated-graph-convolutional-network","title":"Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition","date":"2020-08-09","arxiv_id":"2008.03791","repositories_listed":3,"syntology":null},{"url":"/paper/1st-place-solution-for-ava-kinetics-crossover","slug":"1st-place-solution-for-ava-kinetics-crossover","title":"1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020","date":"2020-06-16","arxiv_id":"2006.09116","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/fast-learning-of-temporal-action-proposal-via","slug":"fast-learning-of-temporal-action-proposal-via","title":"Fast Learning of Temporal Action Proposal via Dense Boundary Generator","date":"2019-11-11","arxiv_id":"1911.04127","repositories_listed":3,"syntology":null},{"url":"/paper/what-makes-training-multi-modal-networks-hard","slug":"what-makes-training-multi-modal-networks-hard","title":"What Makes Training Multi-Modal Classification Networks Hard?","date":"2019-05-29","arxiv_id":"1905.12681","repositories_listed":3,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 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) · 6 unverified","sample_list":"/paper/what-makes-training-multi-modal-networks-hard#ran","syntology_url":"https://syntology.ai/paper/1905.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12681"}},"official":null}},{"url":"/paper/richlt-activated-graph-convolutional-network","slug":"richlt-activated-graph-convolutional-network","title":"Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons","date":"2019-05-16","arxiv_id":"1905.06774","repositories_listed":3,"syntology":null},{"url":"/paper/ntu-rgbd-120-a-large-scale-benchmark-for-3d","slug":"ntu-rgbd-120-a-large-scale-benchmark-for-3d","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","date":"2019-05-12","arxiv_id":"1905.04757","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/ntu-rgbd-120-a-large-scale-benchmark-for-3d#ran","syntology_url":"https://syntology.ai/paper/1905.04757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04757"}},"official":null}},{"url":"/paper/large-scale-weakly-supervised-pre-training","slug":"large-scale-weakly-supervised-pre-training","title":"Large-scale weakly-supervised pre-training for video action recognition","date":"2019-05-02","arxiv_id":"1905.00561","repositories_listed":3,"syntology":{"n":21,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/large-scale-weakly-supervised-pre-training#ran","syntology_url":"https://syntology.ai/paper/1905.00561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00561"}},"official":null}},{"url":"/paper/unsupervised-feature-learning-of-human","slug":"unsupervised-feature-learning-of-human","title":"Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifold","date":"2018-12-06","arxiv_id":"1812.02592","repositories_listed":3,"syntology":null},{"url":"/paper/towards-privacy-preserving-visual-recognition","slug":"towards-privacy-preserving-visual-recognition","title":"Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study","date":"2018-07-22","arxiv_id":"1807.08379","repositories_listed":3,"syntology":null},{"url":"/paper/sparse-adversarial-perturbations-for-videos","slug":"sparse-adversarial-perturbations-for-videos","title":"Sparse Adversarial Perturbations for Videos","date":"2018-03-07","arxiv_id":"1803.02536","repositories_listed":3,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-by","slug":"weakly-supervised-action-localization-by","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","date":"2017-12-14","arxiv_id":"1712.05080","repositories_listed":3,"syntology":null},{"url":"/paper/temporal-3d-convnets-new-architecture-and","slug":"temporal-3d-convnets-new-architecture-and","title":"Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification","date":"2017-11-22","arxiv_id":"1711.08200","repositories_listed":3,"syntology":null},{"url":"/paper/hidden-two-stream-convolutional-networks-for","slug":"hidden-two-stream-convolutional-networks-for","title":"Hidden Two-Stream Convolutional Networks for Action Recognition","date":"2017-04-02","arxiv_id":"1704.00389","repositories_listed":3,"syntology":null},{"url":"/paper/action-recognition-with-dynamic-image","slug":"action-recognition-with-dynamic-image","title":"Action Recognition with Dynamic Image Networks","date":"2016-12-02","arxiv_id":"1612.00738","repositories_listed":3,"syntology":null},{"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/counterfactual-gradients-based-quantification","slug":"counterfactual-gradients-based-quantification","title":"Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks","date":"2024-05-22","arxiv_id":"2405.13758","repositories_listed":2,"syntology":null},{"url":"/paper/leveraging-temporal-contextualization-for","slug":"leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","arxiv_id":"2404.09490","repositories_listed":2,"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":4,"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/leveraging-temporal-contextualization-for#ran","syntology_url":"https://syntology.ai/paper/2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}},"official":{"repos":["naver-ai/tc-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/boosting-adversarial-transferability-across","slug":"boosting-adversarial-transferability-across","title":"Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping","date":"2024-02-06","arxiv_id":"2402.03951","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boosting-adversarial-transferability-across#ran","syntology_url":"https://syntology.ai/paper/2402.03951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03951"}},"official":{"repos":["linqinliang/decowa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"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/joint-adversarial-and-collaborative-learning","slug":"joint-adversarial-and-collaborative-learning","title":"Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition","date":"2023-07-15","arxiv_id":"2307.07791","repositories_listed":2,"syntology":null},{"url":"/paper/riemannian-multiclass-logistics-regression","slug":"riemannian-multiclass-logistics-regression","title":"Riemannian Multinomial Logistics Regression for SPD Neural Networks","date":"2023-05-18","arxiv_id":"2305.11288","repositories_listed":2,"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":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) · 0 unverified","sample_list":"/paper/riemannian-multiclass-logistics-regression#ran","syntology_url":"https://syntology.ai/paper/2305.11288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11288"}},"official":{"repos":["gitzh-chen/spdmlr"],"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/rhm-robot-house-multi-view-human-activity","slug":"rhm-robot-house-multi-view-human-activity","title":"RHM: Robot House Multi-view Human Activity Recognition Dataset","date":"2023-04-24","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/harflow3d-a-latency-oriented-3d-cnn","slug":"harflow3d-a-latency-oriented-3d-cnn","title":"HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA Devices","date":"2023-03-30","arxiv_id":"2303.17218","repositories_listed":2,"syntology":null},{"url":"/paper/video-action-recognition-collaborative","slug":"video-action-recognition-collaborative","title":"Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer","date":"2023-02-17","arxiv_id":"2302.09187","repositories_listed":2,"syntology":null},{"url":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","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":0,"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/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}},"official":{"repos":["opengvlab/internvideo"],"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/where-a-strong-backbone-meets-strong-features","slug":"where-a-strong-backbone-meets-strong-features","title":"Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge","date":"2022-11-16","arxiv_id":"2211.09074","repositories_listed":2,"syntology":null},{"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/weakly-supervised-action-localization-via","slug":"weakly-supervised-action-localization-via","title":"Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning","date":"2022-06-22","arxiv_id":"2206.11011","repositories_listed":2,"syntology":null},{"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/gate-shift-fuse-for-video-action-recognition","slug":"gate-shift-fuse-for-video-action-recognition","title":"Gate-Shift-Fuse for Video Action Recognition","date":"2022-03-16","arxiv_id":"2203.08897","repositories_listed":2,"syntology":null},{"url":"/paper/contextualized-spatio-temporal-contrastive","slug":"contextualized-spatio-temporal-contrastive","title":"Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision","date":"2021-12-09","arxiv_id":"2112.05181","repositories_listed":2,"syntology":null},{"url":"/paper/tada-temporally-adaptive-convolutions-for-1","slug":"tada-temporally-adaptive-convolutions-for-1","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","date":"2021-10-12","arxiv_id":"2110.06178","repositories_listed":2,"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/tada-temporally-adaptive-convolutions-for-1#ran","syntology_url":"https://syntology.ai/paper/2110.06178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06178"}},"official":{"repos":["alibaba-mmai-research/pytorch-video-understanding"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"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/actionclip-a-new-paradigm-for-video-action","slug":"actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/actionclip-a-new-paradigm-for-video-action#ran","syntology_url":"https://syntology.ai/paper/2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}},"official":{"repos":["sallymmx/actionclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-consensus-network-for-weakly","slug":"cross-modal-consensus-network-for-weakly","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","date":"2021-07-27","arxiv_id":"2107.12589","repositories_listed":2,"syntology":null},{"url":"/paper/keeping-your-eye-on-the-ball-trajectory","slug":"keeping-your-eye-on-the-ball-trajectory","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","date":"2021-06-09","arxiv_id":"2106.05392","repositories_listed":2,"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":2,"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/keeping-your-eye-on-the-ball-trajectory#ran","syntology_url":"https://syntology.ai/paper/2106.05392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05392"}},"official":{"repos":["facebookresearch/Motionformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/acm-net-action-context-modeling-network-for","slug":"acm-net-action-context-modeling-network-for","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","date":"2021-04-07","arxiv_id":"2104.02967","repositories_listed":2,"syntology":null},{"url":"/paper/features-understanding-in-3d-cnns-for-actions","slug":"features-understanding-in-3d-cnns-for-actions","title":"Features Understanding in 3D CNNs for Actions Recognition in Video","date":"2020-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/convgru-in-fine-grained-pitching-action","slug":"convgru-in-fine-grained-pitching-action","title":"ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome Prediction","date":"2020-08-18","arxiv_id":"2008.07819","repositories_listed":2,"syntology":null},{"url":"/paper/integralaction-pose-driven-feature","slug":"integralaction-pose-driven-feature","title":"IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos","date":"2020-07-13","arxiv_id":"2007.06317","repositories_listed":2,"syntology":null},{"url":"/paper/background-modeling-via-uncertainty","slug":"background-modeling-via-uncertainty","title":"Weakly-supervised Temporal Action Localization by Uncertainty Modeling","date":"2020-06-12","arxiv_id":"2006.07006","repositories_listed":2,"syntology":null},{"url":"/paper/rise-video-dataset-recognizing-industrial","slug":"rise-video-dataset-recognizing-industrial","title":"Project RISE: Recognizing Industrial Smoke Emissions","date":"2020-05-13","arxiv_id":"2005.06111","repositories_listed":2,"syntology":null},{"url":"/paper/improved-residual-networks-for-image-and","slug":"improved-residual-networks-for-image-and","title":"Improved Residual Networks for Image and Video Recognition","date":"2020-04-10","arxiv_id":"2004.04989","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/improved-residual-networks-for-image-and#ran","syntology_url":"https://syntology.ai/paper/2004.04989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04989"}},"official":{"repos":["iduta/iresnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dmcl-distillation-multiple-choice-learning","slug":"dmcl-distillation-multiple-choice-learning","title":"DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition","date":"2019-12-23","arxiv_id":"1912.10982","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":4,"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/dmcl-distillation-multiple-choice-learning#ran","syntology_url":"https://syntology.ai/paper/1912.10982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.10982"}},"official":{"repos":["ncgarcia/DMCL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/skeleton-based-action-recognition-with-multi","slug":"skeleton-based-action-recognition-with-multi","title":"Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks","date":"2019-12-15","arxiv_id":"1912.06971","repositories_listed":2,"syntology":null},{"url":"/paper/learning-sparse-2d-temporal-adjacent-networks","slug":"learning-sparse-2d-temporal-adjacent-networks","title":"Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization","date":"2019-12-08","arxiv_id":"1912.03612","repositories_listed":2,"syntology":null},{"url":"/paper/background-suppression-network-for-weakly","slug":"background-suppression-network-for-weakly","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","date":"2019-11-22","arxiv_id":"1911.09963","repositories_listed":2,"syntology":null},{"url":"/paper/human-activity-recognition-from-skeleton","slug":"human-activity-recognition-from-skeleton","title":"Human activity recognition from skeleton poses","date":"2019-08-20","arxiv_id":"1908.08928","repositories_listed":2,"syntology":null},{"url":"/paper/what-would-you-expect-anticipating-egocentric","slug":"what-would-you-expect-anticipating-egocentric","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","date":"2019-05-22","arxiv_id":"1905.09035","repositories_listed":2,"syntology":null},{"url":"/paper/semantics-guided-neural-networks-for","slug":"semantics-guided-neural-networks-for","title":"Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition","date":"2019-04-02","arxiv_id":"1904.01189","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/semantics-guided-neural-networks-for#ran","syntology_url":"https://syntology.ai/paper/1904.01189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01189"}},"official":{"repos":["microsoft/SGN"],"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":["listed","official"]}}},{"url":"/paper/au-r-cnn-encoding-expert-prior-knowledge-into","slug":"au-r-cnn-encoding-expert-prior-knowledge-into","title":"AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection","date":"2018-12-14","arxiv_id":"1812.05788","repositories_listed":2,"syntology":null},{"url":"/paper/a2-nets-double-attention-networks-1","slug":"a2-nets-double-attention-networks-1","title":"A^2-Nets: Double Attention Networks","date":"2018-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/iterative-projection-and-matching-finding","slug":"iterative-projection-and-matching-finding","title":"Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision","date":"2018-11-29","arxiv_id":"1811.12326","repositories_listed":2,"syntology":null},{"url":"/paper/adversarial-removal-of-gender-from-deep-image","slug":"adversarial-removal-of-gender-from-deep-image","title":"Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations","date":"2018-11-20","arxiv_id":"1811.08489","repositories_listed":2,"syntology":null},{"url":"/paper/hide-and-seek-a-data-augmentation-technique","slug":"hide-and-seek-a-data-augmentation-technique","title":"Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond","date":"2018-11-06","arxiv_id":"1811.02545","repositories_listed":2,"syntology":null},{"url":"/paper/view-adaptive-neural-networks-for-high","slug":"view-adaptive-neural-networks-for-high","title":"View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition","date":"2018-04-20","arxiv_id":"1804.07453","repositories_listed":2,"syntology":{"n":12,"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 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; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/view-adaptive-neural-networks-for-high#ran","syntology_url":"https://syntology.ai/paper/1804.07453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.07453"}},"official":{"repos":["microsoft/View-Adaptive-Neural-Networks-for-Skeleton-based-Human-Action-Recognition"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/2d3d-pose-estimation-and-action-recognition","slug":"2d3d-pose-estimation-and-action-recognition","title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","date":"2018-02-26","arxiv_id":"1802.09232","repositories_listed":2,"syntology":{"n":25,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":20,"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) · 20 unverified","sample_list":"/paper/2d3d-pose-estimation-and-action-recognition#ran","syntology_url":"https://syntology.ai/paper/1802.09232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09232"}},"official":null}},{"url":"/paper/hacs-human-action-clips-and-segments-dataset","slug":"hacs-human-action-clips-and-segments-dataset","title":"HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization","date":"2017-12-26","arxiv_id":"1712.09374","repositories_listed":2,"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/hacs-human-action-clips-and-segments-dataset#ran","syntology_url":"https://syntology.ai/paper/1712.09374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.09374"}},"official":null}},{"url":"/paper/learning-from-video-and-text-via-large-scale","slug":"learning-from-video-and-text-via-large-scale","title":"Learning from Video and Text via Large-Scale Discriminative Clustering","date":"2017-07-27","arxiv_id":"1707.09074","repositories_listed":2,"syntology":null},{"url":"/paper/action-tubelet-detector-for-spatio-temporal","slug":"action-tubelet-detector-for-spatio-temporal","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","date":"2017-05-04","arxiv_id":"1705.01861","repositories_listed":2,"syntology":null},{"url":"/paper/untrimmednets-for-weakly-supervised-action","slug":"untrimmednets-for-weakly-supervised-action","title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection","date":"2017-03-09","arxiv_id":"1703.03329","repositories_listed":2,"syntology":null}],"syntology_records":38,"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":87,"papers_where_code_ran_first_page":"/task/action-recognition/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":15,"url":"/task/action-recognition/papers/2","json":"/task/action-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":15,"url":"/task/action-recognition/papers/3","json":"/task/action-recognition/papers/3.json","rows":100},{"order":"archive","page":4,"of":15,"url":"/task/action-recognition/papers/4","json":"/task/action-recognition/papers/4.json","rows":100},{"order":"archive","page":5,"of":15,"url":"/task/action-recognition/papers/5","json":"/task/action-recognition/papers/5.json","rows":100},{"order":"archive","page":6,"of":15,"url":"/task/action-recognition/papers/6","json":"/task/action-recognition/papers/6.json","rows":100},{"order":"archive","page":7,"of":15,"url":"/task/action-recognition/papers/7","json":"/task/action-recognition/papers/7.json","rows":100},{"order":"archive","page":8,"of":15,"url":"/task/action-recognition/papers/8","json":"/task/action-recognition/papers/8.json","rows":100},{"order":"archive","page":9,"of":15,"url":"/task/action-recognition/papers/9","json":"/task/action-recognition/papers/9.json","rows":100},{"order":"archive","page":10,"of":15,"url":"/task/action-recognition/papers/10","json":"/task/action-recognition/papers/10.json","rows":100},{"order":"archive","page":11,"of":15,"url":"/task/action-recognition/papers/11","json":"/task/action-recognition/papers/11.json","rows":100},{"order":"archive","page":12,"of":15,"url":"/task/action-recognition/papers/12","json":"/task/action-recognition/papers/12.json","rows":100},{"order":"archive","page":13,"of":15,"url":"/task/action-recognition/papers/13","json":"/task/action-recognition/papers/13.json","rows":100},{"order":"archive","page":14,"of":15,"url":"/task/action-recognition/papers/14","json":"/task/action-recognition/papers/14.json","rows":100},{"order":"archive","page":15,"of":15,"url":"/task/action-recognition/papers/15","json":"/task/action-recognition/papers/15.json","rows":77},{"order":"ran","page":1,"of":1,"url":"/task/action-recognition/papers/ran/1","json":"/task/action-recognition/papers/ran/1.json","rows":87}],"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":"fafc19f442ec02ef0c92c5c2883f354f0d53efa8b41a5f389aba6a885f14503d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}