{"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/temporal-localization","name":"Temporal Localization","slug":"temporal-localization","description_markdown":null,"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":153,"papers_with_code":76,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":4,"subtasks":2,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/charades-sta","name":"Charades-STA","full_name":"","num_papers_in_archive":236},{"url":"/dataset/ave","name":"AVE","full_name":"Audio-Visual Event Localization","num_papers_in_archive":103},{"url":"/dataset/vidstg","name":"VidSTG","full_name":"","num_papers_in_archive":29},{"url":"/dataset/tumtraffic-videoqa","name":"TUMTraffic-VideoQA","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/language-based-temporal-localization","name":"Language-Based Temporal Localization"},{"url":"/task/temporal-defect-localization","name":"Temporal Defect Localization"}],"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":2,"rows_per_page":100,"shown":100,"of":153,"of_with_code":76,"tagged_in_all":153,"counts":{"archive_papers_tagged":153,"with_a_code_link":76,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":153,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers 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/tall-temporal-activity-localization-via","slug":"tall-temporal-activity-localization-via","title":"TALL: Temporal Activity Localization via Language Query","date":"2017-05-05","arxiv_id":"1705.02101","repositories_listed":12,"syntology":null},{"url":"/paper/mac-mining-activity-concepts-for-language","slug":"mac-mining-activity-concepts-for-language","title":"MAC: Mining Activity Concepts for Language-based Temporal Localization","date":"2018-11-21","arxiv_id":"1811.08925","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/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"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/egocentric-video-language-pretraining","slug":"egocentric-video-language-pretraining","title":"Egocentric Video-Language Pretraining","date":"2022-06-03","arxiv_id":"2206.01670","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/egocentric-video-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2206.01670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01670"}},"official":{"repos":["showlab/egovlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/temporal-localization-of-moments-in-video","slug":"temporal-localization-of-moments-in-video","title":"Finding Moments in Video Collections Using Natural Language","date":"2019-07-30","arxiv_id":"1907.12763","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/temporal-localization-of-moments-in-video#ran","syntology_url":"https://syntology.ai/paper/1907.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12763"}},"official":null}},{"url":"/paper/190513313","slug":"190513313","title":"Technical Report of the Video Event Reconstruction and Analysis (VERA) System -- Shooter Localization, Models, Interface, and Beyond","date":"2019-05-26","arxiv_id":"1905.13313","repositories_listed":2,"syntology":null},{"url":"/paper/audio-visual-event-localization-in","slug":"audio-visual-event-localization-in","title":"Audio-Visual Event Localization in Unconstrained Videos","date":"2018-03-23","arxiv_id":"1803.08842","repositories_listed":2,"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/audio-visual-event-localization-in#ran","syntology_url":"https://syntology.ai/paper/1803.08842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08842"}},"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/asynchronous-temporal-fields-for-action","slug":"asynchronous-temporal-fields-for-action","title":"Asynchronous Temporal Fields for Action Recognition","date":"2016-12-19","arxiv_id":"1612.06371","repositories_listed":2,"syntology":null},{"url":"/paper/videomolmo-spatio-temporal-grounding-meets","slug":"videomolmo-spatio-temporal-grounding-meets","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","date":"2025-06-05","arxiv_id":"2506.05336","repositories_listed":1,"syntology":null},{"url":"/paper/distime-distribution-based-time","slug":"distime-distribution-based-time","title":"DisTime: Distribution-based Time Representation for Video Large Language Models","date":"2025-05-30","arxiv_id":"2505.24329","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distime-distribution-based-time#ran","syntology_url":"https://syntology.ai/paper/2505.24329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24329"}},"official":{"repos":["josephzpng/distime"],"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/transforming-faces-into-video-stories","slug":"transforming-faces-into-video-stories","title":"Transforming faces into video stories -- VideoFace2.0","date":"2025-05-04","arxiv_id":"2505.02060","repositories_listed":1,"syntology":null},{"url":"/paper/minerva-evaluating-complex-video-reasoning","slug":"minerva-evaluating-complex-video-reasoning","title":"MINERVA: Evaluating Complex Video Reasoning","date":"2025-05-01","arxiv_id":"2505.00681","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-and-multimodal-data-for-daily","slug":"hierarchical-and-multimodal-data-for-daily","title":"Hierarchical and Multimodal Data for Daily Activity Understanding","date":"2025-04-24","arxiv_id":"2504.17696","repositories_listed":1,"syntology":null},{"url":"/paper/atars-an-aerial-traffic-atomic-activity","slug":"atars-an-aerial-traffic-atomic-activity","title":"ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset","date":"2025-03-24","arxiv_id":"2503.18553","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-to-the-unknown-training-free-audio","slug":"adapting-to-the-unknown-training-free-audio","title":"Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds","date":"2025-03-17","arxiv_id":"2503.13693","repositories_listed":1,"syntology":null},{"url":"/paper/crab-a-unified-audio-visual-scene-1","slug":"crab-a-unified-audio-visual-scene-1","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","date":"2025-03-17","arxiv_id":"2503.13068","repositories_listed":1,"syntology":null},{"url":"/paper/videomind-a-chain-of-lora-agent-for-long","slug":"videomind-a-chain-of-lora-agent-for-long","title":"VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning","date":"2025-03-17","arxiv_id":"2503.13444","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videomind-a-chain-of-lora-agent-for-long#ran","syntology_url":"https://syntology.ai/paper/2503.13444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13444"}},"official":{"repos":["yeliudev/VideoMind"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/timeloc-a-unified-end-to-end-framework-for","slug":"timeloc-a-unified-end-to-end-framework-for","title":"TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos","date":"2025-03-09","arxiv_id":"2503.06526","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-multiple-instance-learning-1","slug":"weakly-supervised-multiple-instance-learning-1","title":"Weakly Supervised Multiple Instance Learning for Whale Call Detection and Temporal Localization in Long-Duration Passive Acoustic Monitoring","date":"2025-02-28","arxiv_id":"2502.20838","repositories_listed":1,"syntology":null},{"url":"/paper/knowing-your-target-target-aware-transformer","slug":"knowing-your-target-target-aware-transformer","title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","date":"2025-02-16","arxiv_id":"2502.11168","repositories_listed":1,"syntology":null},{"url":"/paper/llava-st-a-multimodal-large-language-model","slug":"llava-st-a-multimodal-large-language-model","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","date":"2025-01-14","arxiv_id":"2501.08282","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/llava-st-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2501.08282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08282"}},"official":{"repos":["appletea233/llava-st"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/do-current-video-llms-have-strong-ocr","slug":"do-current-video-llms-have-strong-ocr","title":"Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study","date":"2024-12-29","arxiv_id":"2412.20613","repositories_listed":1,"syntology":null},{"url":"/paper/timerefine-temporal-grounding-with-time","slug":"timerefine-temporal-grounding-with-time","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","date":"2024-12-12","arxiv_id":"2412.09601","repositories_listed":1,"syntology":null},{"url":"/paper/timemarker-a-versatile-video-llm-for-long-and","slug":"timemarker-a-versatile-video-llm-for-long-and","title":"TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability","date":"2024-11-27","arxiv_id":"2411.18211","repositories_listed":1,"syntology":null},{"url":"/paper/number-it-temporal-grounding-videos-like","slug":"number-it-temporal-grounding-videos-like","title":"Number it: Temporal Grounding Videos like Flipping Manga","date":"2024-11-15","arxiv_id":"2411.10332","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/number-it-temporal-grounding-videos-like#ran","syntology_url":"https://syntology.ai/paper/2411.10332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10332"}},"official":{"repos":["yongliang-wu/numpro"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/training-free-video-temporal-grounding-using","slug":"training-free-video-temporal-grounding-using","title":"Training-free Video Temporal Grounding using Large-scale Pre-trained Models","date":"2024-08-29","arxiv_id":"2408.16219","repositories_listed":1,"syntology":null},{"url":"/paper/meerkat-audio-visual-large-language-model-for","slug":"meerkat-audio-visual-large-language-model-for","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","date":"2024-07-01","arxiv_id":"2407.01851","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/meerkat-audio-visual-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2407.01851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01851"}},"official":{"repos":["schowdhury671/meerkat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ophnet-a-large-scale-video-benchmark-for","slug":"ophnet-a-large-scale-video-benchmark-for","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","date":"2024-06-11","arxiv_id":"2406.07471","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ophnet-a-large-scale-video-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2406.07471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07471"}},"official":{"repos":["minghu0830/ophnet-benchmark"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/lita-language-instructed-temporal","slug":"lita-language-instructed-temporal","title":"LITA: Language Instructed Temporal-Localization Assistant","date":"2024-03-27","arxiv_id":"2403.19046","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lita-language-instructed-temporal#ran","syntology_url":"https://syntology.ai/paper/2403.19046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19046"}},"official":{"repos":["nvlabs/lita"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skeleton-based-human-action-recognition-with-1","slug":"skeleton-based-human-action-recognition-with-1","title":"Skeleton-Based Human Action Recognition with Noisy Labels","date":"2024-03-15","arxiv_id":"2403.09975","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"]}}},{"url":"/paper/unloc-a-unified-framework-for-video","slug":"unloc-a-unified-framework-for-video","title":"UnLoc: A Unified Framework for Video Localization Tasks","date":"2023-08-21","arxiv_id":"2308.11062","repositories_listed":1,"syntology":null},{"url":"/paper/videoglue-video-general-understanding","slug":"videoglue-video-general-understanding","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models","date":"2023-07-06","arxiv_id":"2307.03166","repositories_listed":1,"syntology":null},{"url":"/paper/dense-video-object-captioning-from-disjoint","slug":"dense-video-object-captioning-from-disjoint","title":"Dense Video Object Captioning from Disjoint Supervision","date":"2023-06-20","arxiv_id":"2306.11729","repositories_listed":1,"syntology":null},{"url":"/paper/self-chained-image-language-model-for-video-1","slug":"self-chained-image-language-model-for-video-1","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","date":"2023-05-11","arxiv_id":"2305.06988","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-chained-image-language-model-for-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.06988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06988"}},"official":{"repos":["yui010206/sevila"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-classification-to-improve-the","slug":"unsupervised-classification-to-improve-the","title":"Unsupervised classification to improve the quality of a bird song recording dataset","date":"2023-02-15","arxiv_id":"2302.07560","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-learning-of-object-state-changes","slug":"multi-task-learning-of-object-state-changes","title":"Multi-Task Learning of Object State Changes from Uncurated Videos","date":"2022-11-24","arxiv_id":"2211.13500","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/multi-task-learning-of-object-state-changes#ran","syntology_url":"https://syntology.ai/paper/2211.13500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13500"}},"official":{"repos":["soCzech/MultiTaskObjectStates"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/masked-autoencoders-for-egocentric-video","slug":"masked-autoencoders-for-egocentric-video","title":"Masked Autoencoders for Egocentric Video Understanding @ Ego4D Challenge 2022","date":"2022-11-18","arxiv_id":"2211.15286","repositories_listed":1,"syntology":null},{"url":"/paper/locvtp-video-text-pre-training-for-temporal","slug":"locvtp-video-text-pre-training-for-temporal","title":"LocVTP: Video-Text Pre-training for Temporal Localization","date":"2022-07-21","arxiv_id":"2207.10362","repositories_listed":1,"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/locvtp-video-text-pre-training-for-temporal#ran","syntology_url":"https://syntology.ai/paper/2207.10362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10362"}},"official":{"repos":["mengcaopku/locvtp"],"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/tadml-a-fast-temporal-action-detection-with","slug":"tadml-a-fast-temporal-action-detection-with","title":"TadML: A fast temporal action detection with Mechanics-MLP","date":"2022-06-07","arxiv_id":"2206.02997","repositories_listed":1,"syntology":null},{"url":"/paper/stargazer-a-transformer-based-driver-action","slug":"stargazer-a-transformer-based-driver-action","title":"Stargazer: A transformer-based driver action detection system for intelligent transportation","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temporally-precise-action-spotting-in-soccer","slug":"temporally-precise-action-spotting-in-soccer","title":"Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors","date":"2022-05-20","arxiv_id":"2205.10450","repositories_listed":1,"syntology":null},{"url":"/paper/tubedetr-spatio-temporal-video-grounding-with","slug":"tubedetr-spatio-temporal-video-grounding-with","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","date":"2022-03-30","arxiv_id":"2203.16434","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/tubedetr-spatio-temporal-video-grounding-with#ran","syntology_url":"https://syntology.ai/paper/2203.16434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16434"}},"official":{"repos":["antoyang/TubeDETR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-pre-training-for-temporal-action","slug":"unsupervised-pre-training-for-temporal-action","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","date":"2022-03-25","arxiv_id":"2203.13609","repositories_listed":1,"syntology":null},{"url":"/paper/opental-towards-open-set-temporal-action","slug":"opental-towards-open-set-temporal-action","title":"OpenTAL: Towards Open Set Temporal Action Localization","date":"2022-03-10","arxiv_id":"2203.05114","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/opental-towards-open-set-temporal-action#ran","syntology_url":"https://syntology.ai/paper/2203.05114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05114"}},"official":{"repos":["Cogito2012/OpenTAL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-semi-supervised-learning-for-video","slug":"end-to-end-semi-supervised-learning-for-video","title":"End-to-End Semi-Supervised Learning for Video Action Detection","date":"2022-03-08","arxiv_id":"2203.04251","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-semi-supervised-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2203.04251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04251"}},"official":{"repos":["AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection"],"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/when-did-it-happen-duration-informed-temporal","slug":"when-did-it-happen-duration-informed-temporal","title":"When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs","date":"2022-02-16","arxiv_id":"2202.08138","repositories_listed":1,"syntology":null},{"url":"/paper/explore-and-match-end-to-end-video-grounding","slug":"explore-and-match-end-to-end-video-grounding","title":"Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos","date":"2022-01-25","arxiv_id":"2201.10168","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-deep-residual-reasoning-for","slug":"hierarchical-deep-residual-reasoning-for","title":"Hierarchical Deep Residual Reasoning for Temporal Moment Localization","date":"2021-10-31","arxiv_id":"2111.00417","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-temporal-action-localization-with","slug":"few-shot-temporal-action-localization-with","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","date":"2021-10-20","arxiv_id":"2110.10552","repositories_listed":1,"syntology":null},{"url":"/paper/a-bottom-up-method-towards-the-automatic-and","slug":"a-bottom-up-method-towards-the-automatic-and","title":"A Bottom-up method Towards the Automatic and Objective Monitoring of Smoking Behavior In-the-wild using Wrist-mounted Inertial Sensors","date":"2021-09-08","arxiv_id":"2109.03475","repositories_listed":1,"syntology":null},{"url":"/paper/enriching-local-and-global-contexts-for","slug":"enriching-local-and-global-contexts-for","title":"Enriching Local and Global Contexts for Temporal Action Localization","date":"2021-07-27","arxiv_id":"2107.12960","repositories_listed":1,"syntology":null},{"url":"/paper/naaqa-a-neural-architecture-for-acoustic","slug":"naaqa-a-neural-architecture-for-acoustic","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","date":"2021-06-11","arxiv_id":"2106.06147","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/naaqa-a-neural-architecture-for-acoustic#ran","syntology_url":"https://syntology.ai/paper/2106.06147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06147"}},"official":null}},{"url":"/paper/fineaction-a-fined-video-dataset-for-temporal","slug":"fineaction-a-fined-video-dataset-for-temporal","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","date":"2021-05-24","arxiv_id":"2105.11107","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-selection-learning","slug":"weakly-supervised-action-selection-learning","title":"Weakly Supervised Action Selection Learning in Video","date":"2021-05-06","arxiv_id":"2105.02439","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/weakly-supervised-action-selection-learning#ran","syntology_url":"https://syntology.ai/paper/2105.02439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02439"}},"official":{"repos":["layer6ai-labs/ASL"],"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/learning-salient-boundary-feature-for-anchor","slug":"learning-salient-boundary-feature-for-anchor","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","date":"2021-03-24","arxiv_id":"2103.13137","repositories_listed":1,"syntology":null},{"url":"/paper/cityflow-nl-tracking-and-retrieval-of","slug":"cityflow-nl-tracking-and-retrieval-of","title":"CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions","date":"2021-01-12","arxiv_id":"2101.04741","repositories_listed":1,"syntology":null},{"url":"/paper/tsp-temporally-sensitive-pretraining-of-video","slug":"tsp-temporally-sensitive-pretraining-of-video","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","date":"2020-11-23","arxiv_id":"2011.11479","repositories_listed":1,"syntology":null},{"url":"/paper/boundary-sensitive-pre-training-for-temporal","slug":"boundary-sensitive-pre-training-for-temporal","title":"Boundary-sensitive Pre-training for Temporal Localization in Videos","date":"2020-11-21","arxiv_id":"2011.10830","repositories_listed":1,"syntology":null},{"url":"/paper/vlg-net-video-language-graph-matching-network","slug":"vlg-net-video-language-graph-matching-network","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","date":"2020-11-19","arxiv_id":"2011.10132","repositories_listed":1,"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/vlg-net-video-language-graph-matching-network#ran","syntology_url":"https://syntology.ai/paper/2011.10132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.10132"}},"official":null}},{"url":"/paper/human-centric-spatio-temporal-video-grounding","slug":"human-centric-spatio-temporal-video-grounding","title":"Human-centric Spatio-Temporal Video Grounding With Visual Transformers","date":"2020-11-10","arxiv_id":"2011.05049","repositories_listed":1,"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/human-centric-spatio-temporal-video-grounding#ran","syntology_url":"https://syntology.ai/paper/2011.05049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.05049"}},"official":{"repos":["tzhhhh123/HC-STVG"],"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/accelerating-covid-19-differential-diagnosis","slug":"accelerating-covid-19-differential-diagnosis","title":"Accelerating COVID-19 Differential Diagnosis with Explainable Ultrasound Image Analysis","date":"2020-09-13","arxiv_id":"2009.06116","repositories_listed":1,"syntology":null},{"url":"/paper/video-moment-localization-using-object","slug":"video-moment-localization-using-object","title":"Video Moment Localization using Object Evidence and Reverse Captioning","date":"2020-06-18","arxiv_id":"2006.10260","repositories_listed":1,"syntology":null},{"url":"/paper/dense-caption-matching-and-frame-selection","slug":"dense-caption-matching-and-frame-selection","title":"Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA","date":"2020-05-13","arxiv_id":"2005.06409","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dense-caption-matching-and-frame-selection#ran","syntology_url":"https://syntology.ai/paper/2005.06409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.06409"}},"official":{"repos":["hyounghk/VideoQADenseCapFrameGate-ACL2020"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/weakly-supervised-temporal-action-1","slug":"weakly-supervised-temporal-action-1","title":"Weakly Supervised Temporal Action Localization Using Deep Metric Learning","date":"2020-01-21","arxiv_id":"2001.07793","repositories_listed":1,"syntology":null},{"url":"/paper/why-cant-i-dance-in-the-mall-learning-to-1","slug":"why-cant-i-dance-in-the-mall-learning-to-1","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","date":"2019-12-11","arxiv_id":"1912.05534","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/why-cant-i-dance-in-the-mall-learning-to-1#ran","syntology_url":"https://syntology.ai/paper/1912.05534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05534"}},"official":{"repos":["vt-vl-lab/SDN"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-attention-networks-for-temporal","slug":"multi-attention-networks-for-temporal","title":"Multi-attention Networks for Temporal Localization of Video-level Labels","date":"2019-11-15","arxiv_id":"1911.06866","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-localize-temporal-events-in-large","slug":"learning-to-localize-temporal-events-in-large","title":"Learning to Localize Temporal Events in Large-scale Video Data","date":"2019-10-25","arxiv_id":"1910.11631","repositories_listed":1,"syntology":null},{"url":"/paper/softloc-robust-temporal-localization-under","slug":"softloc-robust-temporal-localization-under","title":"SoftLoc: Robust Temporal Localization under Label Misalignment","date":"2019-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/refineloc-iterative-refinement-for-weakly","slug":"refineloc-iterative-refinement-for-weakly","title":"RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization","date":"2019-03-30","arxiv_id":"1904.00227","repositories_listed":1,"syntology":null},{"url":"/paper/am-i-done-predicting-action-progress-in","slug":"am-i-done-predicting-action-progress-in","title":"Am I Done? Predicting Action Progress in Videos","date":"2017-05-04","arxiv_id":"1705.01781","repositories_listed":1,"syntology":null},{"url":"/paper/online-human-action-detection-using-joint","slug":"online-human-action-detection-using-joint","title":"Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks","date":"2016-04-19","arxiv_id":"1604.05633","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-action-localization-in-untrimmed","slug":"temporal-action-localization-in-untrimmed","title":"Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs","date":"2016-01-09","arxiv_id":"1601.02129","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-localization-of-fine-grained-actions","slug":"temporal-localization-of-fine-grained-actions","title":"Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images","date":"2015-04-04","arxiv_id":"1504.00983","repositories_listed":1,"syntology":null},{"url":null,"slug":"fine-tuning-large-audio-language-models-with","title":"Fine-Tuning Large Audio-Language Models with LoRA for Precise Temporal Localization of Prolonged Exposure Therapy Elements","date":"2025-06-11","arxiv_id":"2506.09707","repositories_listed":0,"syntology":null},{"url":null,"slug":"timesoccer-an-end-to-end-multimodal-large","title":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","date":"2025-04-24","arxiv_id":"2504.17365","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-framework-for-relative","title":"A Large-Language Model Framework for Relative Timeline Extraction from PubMed Case Reports","date":"2025-04-15","arxiv_id":"2504.12350","repositories_listed":0,"syntology":null},{"url":null,"slug":"crash-time-matters-hybridmamba-for-fine","title":"Crash Time Matters: HybridMamba for Fine-Grained Temporal Localization in Traffic Surveillance Footage","date":"2025-04-04","arxiv_id":"2504.03235","repositories_listed":0,"syntology":null},{"url":null,"slug":"socialgesture-delving-into-multi-person","title":"SocialGesture: Delving into Multi-person Gesture Understanding","date":"2025-04-03","arxiv_id":"2504.02244","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-and-learn-leveraging-expert-knowledge","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","date":"2025-03-14","arxiv_id":"2503.11392","repositories_listed":0,"syntology":null},{"url":null,"slug":"measure-twice-cut-once-grasping-video","title":"Measure Twice, Cut Once: Grasping Video Structures and Event Semantics with LLMs for Video Temporal Localization","date":"2025-03-12","arxiv_id":"2503.09027","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fine-grained-video-question-answering","title":"Towards Fine-Grained Video Question Answering","date":"2025-03-10","arxiv_id":"2503.06820","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-of-millimeter-wave-radar-and-pulse","title":"Fusion of Millimeter-wave Radar and Pulse Oximeter Data for Low-burden Diagnosis of Obstructive Sleep Apnea-Hypopnea Syndrome","date":"2025-01-25","arxiv_id":"2501.15264","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudo-strong-labels-from-frame-level","title":"Pseudo Strong Labels from Frame-Level Predictions for Weakly Supervised Sound Event Detection","date":"2025-01-07","arxiv_id":"2501.03740","repositories_listed":0,"syntology":null},{"url":null,"slug":"shotvl-human-centric-highlight-frame","title":"ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries","date":"2024-12-17","arxiv_id":"2412.12675","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-detection-and-classification-of","title":"Unsupervised detection and classification of heartbeats using the dissimilarity matrix in PCG signals","date":"2024-11-05","arxiv_id":"2411.03061","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-sleep-apnea-hypopnea-events","title":"Detection of Sleep Apnea-Hypopnea Events Using Millimeter-wave Radar and Pulse Oximeter","date":"2024-09-28","arxiv_id":"2409.19217","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-noisy-labels-on-sound-event","title":"Impact of Noisy Labels on Sound Event Detection: Deletion Errors Are More Detrimental Than Insertion Errors","date":"2024-08-27","arxiv_id":"2408.14771","repositories_listed":0,"syntology":null},{"url":null,"slug":"described-spatial-temporal-video-detection","title":"Described Spatial-Temporal Video Detection","date":"2024-07-08","arxiv_id":"2407.05610","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllm-as-video-narrator-mitigating-modality","title":"MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval","date":"2024-06-25","arxiv_id":"2406.17880","repositories_listed":0,"syntology":null},{"url":null,"slug":"avicuna-audio-visual-llm-with-interleaver-and","title":"Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding","date":"2024-03-24","arxiv_id":"2403.16276","repositories_listed":0,"syntology":null},{"url":null,"slug":"density-guided-label-smoothing-for-temporal","title":"Density-Guided Label Smoothing for Temporal Localization of Driving Actions","date":"2024-03-11","arxiv_id":"2403.06616","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-fusion-of-2d-pose-and","title":"Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition","date":"2024-03-11","arxiv_id":"2403.06577","repositories_listed":0,"syntology":null},{"url":null,"slug":"olvit-multi-modal-state-tracking-via","title":"OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog","date":"2024-02-20","arxiv_id":"2402.13146","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-assisted-analysis-of-cataract","title":"Deep-Learning-Assisted Analysis of Cataract Surgery Videos","date":"2023-12-10","arxiv_id":"2312.05900","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-action-recognition-spotting-and","title":"Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives","date":"2023-09-21","arxiv_id":"2309.12067","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-video-contextual-knowledge-exploration","title":"Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization","date":"2023-08-24","arxiv_id":"2308.12609","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-stage-visual-query-localization-in","title":"Single-Stage Visual Query Localization in Egocentric Videos","date":"2023-06-15","arxiv_id":"2306.09324","repositories_listed":0,"syntology":null}],"syntology_records":25,"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":24,"papers_where_code_ran_first_page":"/task/temporal-localization/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":2,"url":"/task/temporal-localization/papers/2","json":"/task/temporal-localization/papers/2.json","rows":53},{"order":"ran","page":1,"of":1,"url":"/task/temporal-localization/papers/ran/1","json":"/task/temporal-localization/papers/ran/1.json","rows":24}],"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":"e9b5752d055020ca13cd1f1014081a9e91274451dc014c04ddc7d17d668b1d6d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}