{"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/video-grounding","name":"Video Grounding","slug":"video-grounding","description_markdown":"**Video grounding** is the task of linking spoken language descriptions to specific video segments. In video grounding, the model is given a video and a natural language description, such as a sentence or a caption, and its goal is to identify the specific segment of the video that corresponds to the description. This can involve tasks such as localizing the objects or actions mentioned in the description within the video, or associating a specific time interval with the description.","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":114,"papers_with_code":56,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":10,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-grounding-on-qvhighlights","slug":"video-grounding-on-qvhighlights","dataset":"QVHighlights","dataset_url":"/dataset/qvhighlights","rows_in_archive":7,"metrics":["R@1,IoU=0.7","R@1,IoU=0.5"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/video-grounding-on-mad","slug":"video-grounding-on-mad","dataset":"MAD","dataset_url":"/dataset/mad","rows_in_archive":2,"metrics":["R@1,IoU=0.1","R@5,IoU=0.1","R@10,IoU=0.1","R@100,IoU=0.1","R@50,IoU=0.1","R@1,IoU=0.3","R@5,IoU=0.3"],"first_row_in_archive_order":{"model":"DeCafNet","paper_title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","paper_url":"/paper/decafnet-delegate-and-conquer-for-efficient","paper_date":"2025-05-22","arxiv_id":"2505.16376","code_links":[{"title":"zijialewislu/cvpr2025-decafnet","url":"https://github.com/zijialewislu/cvpr2025-decafnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/qvhighlights","name":"QVHighlights","full_name":"Query-based Video Highlights","num_papers_in_archive":41},{"url":"/dataset/mad","name":"MAD","full_name":"","num_papers_in_archive":36},{"url":"/dataset/animal-kingdom","name":"Animal Kingdom","full_name":"","num_papers_in_archive":26},{"url":"/dataset/situated-reasoning-star","name":"STAR Benchmark","full_name":"Situated Reasoning","num_papers_in_archive":17},{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":"","num_papers_in_archive":8},{"url":"/dataset/longvale","name":"LongVALE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/kinetic-gebc","name":"Kinetics-GEB+","full_name":"","num_papers_in_archive":1},{"url":"/dataset/youwikihow","name":"YouwikiHow","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vript","name":"Vript","full_name":"🎬 Vript: A Video Is Worth Thousands of Words","num_papers_in_archive":0}],"subtasks":[{"url":"/task/boundary-grounding","name":"Boundary Grounding"},{"url":"/task/video-narrative-grounding","name":"Video Narrative Grounding"}],"parent_tasks":[{"url":"/task/video-retrieval","name":"Video Retrieval"}],"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":114,"of_with_code":56,"tagged_in_all":114,"counts":{"archive_papers_tagged":114,"with_a_code_link":56,"where_syntology_ran_a_sample":23,"not_listed_spam_title":0,"listed":114,"listed_where_code_ran":23,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":21,"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/umt-unified-multi-modal-transformers-for","slug":"umt-unified-multi-modal-transformers-for","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","date":"2022-03-23","arxiv_id":"2203.12745","repositories_listed":3,"syntology":null},{"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/context-guided-spatio-temporal-video","slug":"context-guided-spatio-temporal-video","title":"Context-Guided Spatio-Temporal Video Grounding","date":"2024-01-03","arxiv_id":"2401.01578","repositories_listed":2,"syntology":{"n":34,"n_ran":22,"n_constructed":0,"n_ran_checked":12,"n_instrument":10,"n_unverified":12,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":34,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 10 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/context-guided-spatio-temporal-video#ran","syntology_url":"https://syntology.ai/paper/2401.01578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01578"}},"official":{"repos":["henglan/cgstvg"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":12,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/negative-sample-matters-a-renaissance-of","slug":"negative-sample-matters-a-renaissance-of","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","date":"2021-09-10","arxiv_id":"2109.04872","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-tuning-for-videollms","slug":"reinforcement-learning-tuning-for-videollms","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","date":"2025-06-02","arxiv_id":"2506.01908","repositories_listed":1,"syntology":{"n":17,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"10 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/reinforcement-learning-tuning-for-videollms#ran","syntology_url":"https://syntology.ai/paper/2506.01908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01908"}},"official":{"repos":["appletea233/temporal-r1"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/decafnet-delegate-and-conquer-for-efficient","slug":"decafnet-delegate-and-conquer-for-efficient","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","date":"2025-05-22","arxiv_id":"2505.16376","repositories_listed":1,"syntology":null},{"url":"/paper/object-shot-enhanced-grounding-network-for","slug":"object-shot-enhanced-grounding-network-for","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","date":"2025-05-07","arxiv_id":"2505.04270","repositories_listed":1,"syntology":{"n":17,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"7 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; 4 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/object-shot-enhanced-grounding-network-for#ran","syntology_url":"https://syntology.ai/paper/2505.04270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04270"}},"official":{"repos":["yisen-feng/osgnet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/timezero-temporal-video-grounding-with","slug":"timezero-temporal-video-grounding-with","title":"TimeZero: Temporal Video Grounding with Reasoning-Guided LVLM","date":"2025-03-17","arxiv_id":"2503.13377","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timezero-temporal-video-grounding-with#ran","syntology_url":"https://syntology.ai/paper/2503.13377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13377"}},"official":{"repos":["www-ye/timezero"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/omnistvg-toward-spatio-temporal-omni-object","slug":"omnistvg-toward-spatio-temporal-omni-object","title":"OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding","date":"2025-03-13","arxiv_id":"2503.10500","repositories_listed":1,"syntology":null},{"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/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/tarsier2-advancing-large-vision-language","slug":"tarsier2-advancing-large-vision-language","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","date":"2025-01-14","arxiv_id":"2501.07888","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tarsier2-advancing-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2501.07888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07888"}},"official":{"repos":["bytedance/tarsier"],"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","unlocated"]}}},{"url":"/paper/vidchain-chain-of-tasks-with-metric-based","slug":"vidchain-chain-of-tasks-with-metric-based","title":"VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning","date":"2025-01-12","arxiv_id":"2501.06761","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-of-compositional-generalization","slug":"consistency-of-compositional-generalization","title":"Consistency of Compositional Generalization across Multiple Levels","date":"2024-12-18","arxiv_id":"2412.13636","repositories_listed":1,"syntology":null},{"url":"/paper/videollm-knows-when-to-speak-enhancing-time","slug":"videollm-knows-when-to-speak-enhancing-time","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","date":"2024-11-27","arxiv_id":"2411.17991","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videollm-knows-when-to-speak-enhancing-time#ran","syntology_url":"https://syntology.ai/paper/2411.17991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17991"}},"official":{"repos":["yellow-binary-tree/mmduet"],"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/prior-knowledge-integration-via-llm-encoding","slug":"prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","arxiv_id":"2407.15051","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prior-knowledge-integration-via-llm-encoding#ran","syntology_url":"https://syntology.ai/paper/2407.15051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15051"}},"official":{"repos":["fletcherjiang/llmepet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/artemis-towards-referential-understanding-in","slug":"artemis-towards-referential-understanding-in","title":"Artemis: Towards Referential Understanding in Complex Videos","date":"2024-06-01","arxiv_id":"2406.00258","repositories_listed":1,"syntology":null},{"url":"/paper/snag-scalable-and-accurate-video-grounding","slug":"snag-scalable-and-accurate-video-grounding","title":"SnAG: Scalable and Accurate Video Grounding","date":"2024-04-02","arxiv_id":"2404.02257","repositories_listed":1,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":16,"phrase":"13 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; 9 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/snag-scalable-and-accurate-video-grounding#ran","syntology_url":"https://syntology.ai/paper/2404.02257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02257"}},"official":null}},{"url":"/paper/unified-static-and-dynamic-network-efficient","slug":"unified-static-and-dynamic-network-efficient","title":"Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding","date":"2024-03-21","arxiv_id":"2403.14174","repositories_listed":1,"syntology":null},{"url":"/paper/hawkeye-training-video-text-llms-for","slug":"hawkeye-training-video-text-llms-for","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","date":"2024-03-15","arxiv_id":"2403.10228","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/hawkeye-training-video-text-llms-for#ran","syntology_url":"https://syntology.ai/paper/2403.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10228"}},"official":{"repos":["yellow-binary-tree/hawkeye"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gaussian-mixture-proposals-with-pull-push","slug":"gaussian-mixture-proposals-with-pull-push","title":"Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding","date":"2023-12-27","arxiv_id":"2312.16388","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-contrastive-learning-with","slug":"cross-modal-contrastive-learning-with","title":"Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment Retrieval","date":"2023-12-12","arxiv_id":"2312.07435","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-question-answering-in-long","slug":"grounded-question-answering-in-long","title":"Grounded Question-Answering in Long Egocentric Videos","date":"2023-12-11","arxiv_id":"2312.06505","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/grounded-question-answering-in-long#ran","syntology_url":"https://syntology.ai/paper/2312.06505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06505"}},"official":{"repos":["becomebright/groundvqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vtimellm-empower-llm-to-grasp-video-moments","slug":"vtimellm-empower-llm-to-grasp-video-moments","title":"VTimeLLM: Empower LLM to Grasp Video Moments","date":"2023-11-30","arxiv_id":"2311.18445","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vtimellm-empower-llm-to-grasp-video-moments#ran","syntology_url":"https://syntology.ai/paper/2311.18445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18445"}},"official":{"repos":["huangb23/vtimellm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-the-gap-a-unified-video","slug":"bridging-the-gap-a-unified-video","title":"Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection","date":"2023-11-28","arxiv_id":"2311.16464","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"9 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bridging-the-gap-a-unified-video#ran","syntology_url":"https://syntology.ai/paper/2311.16464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16464"}},"official":{"repos":["easonxiao-888/uvcom"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pg-video-llava-pixel-grounding-large-video","slug":"pg-video-llava-pixel-grounding-large-video","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","date":"2023-11-22","arxiv_id":"2311.13435","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pg-video-llava-pixel-grounding-large-video#ran","syntology_url":"https://syntology.ai/paper/2311.13435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13435"}},"official":{"repos":["mbzuai-oryx/video-llava"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-iterative-refinement-with-diffusion","slug":"exploring-iterative-refinement-with-diffusion","title":"Exploring Iterative Refinement with Diffusion Models for Video Grounding","date":"2023-10-26","arxiv_id":"2310.17189","repositories_listed":1,"syntology":null},{"url":"/paper/dual-path-temporal-map-optimization-for-make","slug":"dual-path-temporal-map-optimization-for-make","title":"Dual-Path Temporal Map Optimization for Make-up Temporal Video Grounding","date":"2023-09-12","arxiv_id":"2309.06176","repositories_listed":1,"syntology":null},{"url":"/paper/can-i-trust-your-answer-visually-grounded","slug":"can-i-trust-your-answer-visually-grounded","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","date":"2023-09-04","arxiv_id":"2309.01327","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/can-i-trust-your-answer-visually-grounded#ran","syntology_url":"https://syntology.ai/paper/2309.01327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01327"}},"official":{"repos":["doc-doc/next-gqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/knowing-where-to-focus-event-aware","slug":"knowing-where-to-focus-event-aware","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","date":"2023-08-14","arxiv_id":"2308.06947","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 ran (of which 1 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) · 2 unverified","sample_list":"/paper/knowing-where-to-focus-event-aware#ran","syntology_url":"https://syntology.ai/paper/2308.06947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06947"}},"official":{"repos":["jinhyunj/eatr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/boundary-denoising-for-video-activity","slug":"boundary-denoising-for-video-activity","title":"Boundary-Denoising for Video Activity Localization","date":"2023-04-06","arxiv_id":"2304.02934","repositories_listed":1,"syntology":null},{"url":"/paper/query-dependent-video-representation-for","slug":"query-dependent-video-representation-for","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","date":"2023-03-24","arxiv_id":"2303.13874","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/query-dependent-video-representation-for#ran","syntology_url":"https://syntology.ai/paper/2303.13874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13874"}},"official":{"repos":["wjun0830/qd-detr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/text-visual-prompting-for-efficient-2d","slug":"text-visual-prompting-for-efficient-2d","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","date":"2023-03-09","arxiv_id":"2303.04995","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/text-visual-prompting-for-efficient-2d#ran","syntology_url":"https://syntology.ai/paper/2303.04995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04995"}},"official":{"repos":["intel/TVP"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/localizing-moments-in-long-video-via","slug":"localizing-moments-in-long-video-via","title":"Localizing Moments in Long Video Via Multimodal Guidance","date":"2023-02-26","arxiv_id":"2302.13372","repositories_listed":1,"syntology":null},{"url":"/paper/minotaur-multi-task-video-grounding-from","slug":"minotaur-multi-task-video-grounding-from","title":"MINOTAUR: Multi-task Video Grounding From Multimodal Queries","date":"2023-02-16","arxiv_id":"2302.08063","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-effect-of-primitives-for","slug":"exploring-the-effect-of-primitives-for","title":"Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-transformer-based-model-for-ego4d","slug":"a-simple-transformer-based-model-for-ego4d","title":"A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge","date":"2022-11-16","arxiv_id":"2211.08704","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-temporal-article-grounding","slug":"weakly-supervised-temporal-article-grounding","title":"Weakly-Supervised Temporal Article Grounding","date":"2022-10-22","arxiv_id":"2210.12444","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/weakly-supervised-temporal-article-grounding#ran","syntology_url":"https://syntology.ai/paper/2210.12444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12444"}},"official":{"repos":["zjuchenlong/wsag"],"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/embracing-consistency-a-one-stage-approach","slug":"embracing-consistency-a-one-stage-approach","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","date":"2022-09-27","arxiv_id":"2209.13306","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":9,"n_ran_checked":10,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/embracing-consistency-a-one-stage-approach#ran","syntology_url":"https://syntology.ai/paper/2209.13306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.13306"}},"official":{"repos":["jy0205/stcat"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":9,"n_ran_no_instrument_failure":10,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-parameter-efficient-integration-of","slug":"towards-parameter-efficient-integration-of","title":"Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding","date":"2022-09-26","arxiv_id":"2209.13359","repositories_listed":1,"syntology":null},{"url":"/paper/cone-an-efficient-coarse-to-fine-alignment","slug":"cone-an-efficient-coarse-to-fine-alignment","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","date":"2022-09-22","arxiv_id":"2209.10918","repositories_listed":1,"syntology":null},{"url":"/paper/video-guided-curriculum-learning-for-spoken","slug":"video-guided-curriculum-learning-for-spoken","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","date":"2022-09-01","arxiv_id":"2209.00277","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-guided-curriculum-learning-for-spoken#ran","syntology_url":"https://syntology.ai/paper/2209.00277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.00277"}},"official":{"repos":["marmot-xy/spoken-video-grounding"],"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/animal-kingdom-a-large-and-diverse-dataset","slug":"animal-kingdom-a-large-and-diverse-dataset","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","date":"2022-04-18","arxiv_id":"2204.08129","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/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/detecting-moments-and-highlights-in-videos","slug":"detecting-moments-and-highlights-in-videos","title":"Detecting Moments and Highlights in Videos via Natural Language Queries","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vidlankd-improving-language-understanding-via","slug":"vidlankd-improving-language-understanding-via","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","date":"2021-07-06","arxiv_id":"2107.02681","repositories_listed":1,"syntology":null},{"url":"/paper/interventional-video-grounding-with-dual","slug":"interventional-video-grounding-with-dual","title":"Interventional Video Grounding with Dual Contrastive Learning","date":"2021-06-21","arxiv_id":"2106.11013","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-learning-for-audio-visual-video","slug":"cross-modal-learning-for-audio-visual-video","title":"Cross-Modal learning for Audio-Visual Video Parsing","date":"2021-04-03","arxiv_id":"2104.04598","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/dense-regression-network-for-video-grounding","slug":"dense-regression-network-for-video-grounding","title":"Dense Regression Network for Video Grounding","date":"2020-04-07","arxiv_id":"2004.03545","repositories_listed":1,"syntology":null},{"url":"/paper/where-does-it-exist-spatio-temporal-video","slug":"where-does-it-exist-spatio-temporal-video","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","date":"2020-01-19","arxiv_id":"2001.06891","repositories_listed":1,"syntology":null},{"url":"/paper/read-watch-and-move-reinforcement-learning","slug":"read-watch-and-move-reinforcement-learning","title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos","date":"2019-01-21","arxiv_id":"1901.06829","repositories_listed":1,"syntology":null},{"url":null,"slug":"videoitg-multimodal-video-understanding-with","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","date":"2025-07-17","arxiv_id":"2507.13353","repositories_listed":0,"syntology":null},{"url":null,"slug":"sama-towards-multi-turn-referential-grounded","title":"SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models","date":"2025-05-24","arxiv_id":"2505.18812","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-weakly-supervised-video-grounding","title":"Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection","date":"2025-03-29","arxiv_id":"2503.23181","repositories_listed":0,"syntology":null},{"url":null,"slug":"videogem-training-free-action-grounding-in","title":"VideoGEM: Training-free Action Grounding in Videos","date":"2025-03-26","arxiv_id":"2503.20348","repositories_listed":0,"syntology":null},{"url":null,"slug":"spacevllm-endowing-multimodal-large-language","title":"SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability","date":"2025-03-18","arxiv_id":"2503.13983","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-self-paced-learning-for-weakly","title":"Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding","date":"2025-01-28","arxiv_id":"2501.17053","repositories_listed":0,"syntology":null},{"url":null,"slug":"stpro-spatial-and-temporal-progressive","title":"STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-contrastive-learning-for-video","title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","date":"2024-12-10","arxiv_id":"2412.07157","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-llms-for-temporal-reasoning-in-long","title":"Video LLMs for Temporal Reasoning in Long Videos","date":"2024-12-04","arxiv_id":"2412.02930","repositories_listed":0,"syntology":null},{"url":null,"slug":"seq2time-sequential-knowledge-transfer-for","title":"Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding","date":"2024-11-25","arxiv_id":"2411.16932","repositories_listed":0,"syntology":null},{"url":null,"slug":"simbase-a-simple-baseline-for-temporal-video","title":"SimBase: A Simple Baseline for Temporal Video Grounding","date":"2024-11-12","arxiv_id":"2411.07945","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01669","title":"SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses","date":"2024-08-03","arxiv_id":"2408.01669","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-sentence-video-grounding-for-long-video","title":"Multi-sentence Video Grounding for Long Video Generation","date":"2024-07-18","arxiv_id":"2407.13219","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":"autotvg-a-new-vision-language-pre-training","title":"AutoTVG: A New Vision-language Pre-training Paradigm for Temporal Video Grounding","date":"2024-06-11","arxiv_id":"2406.07091","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplify-implant-depth-prediction-as-video","title":"Simplify Implant Depth Prediction as Video Grounding: A Texture Perceive Implant Depth Prediction Network","date":"2024-06-07","arxiv_id":"2406.04603","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-of-thought-step-by-step-video-reasoning","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","date":"2024-05-07","arxiv_id":"2501.03230","repositories_listed":0,"syntology":null},{"url":null,"slug":"spikemba-multi-modal-spiking-saliency-mamba","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","date":"2024-04-01","arxiv_id":"2404.01174","repositories_listed":0,"syntology":null},{"url":null,"slug":"videogrounding-dino-towards-open-vocabulary","title":"VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-groundingdino-towards-open-vocabulary","title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding","date":"2023-12-31","arxiv_id":"2401.00901","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm4vg-large-language-models-evaluation-for","title":"LLM4VG: Large Language Models Evaluation for Video Grounding","date":"2023-12-21","arxiv_id":"2312.14206","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-domain-adaptation-across-video","title":"Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding","date":"2023-12-21","arxiv_id":"2312.13633","repositories_listed":0,"syntology":null},{"url":null,"slug":"etc-temporal-boundary-expand-then-clarify-for","title":"EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model","date":"2023-12-05","arxiv_id":"2312.02483","repositories_listed":0,"syntology":null},{"url":"/paper/diffusionvmr-diffusion-model-for-video-moment","slug":"diffusionvmr-diffusion-model-for-video-moment","title":"DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection","date":"2023-08-29","arxiv_id":"2308.15109","repositories_listed":0,"syntology":null},{"url":null,"slug":"vigt-proposal-free-video-grounding-with","title":"ViGT: Proposal-free Video Grounding with Learnable Token in Transformer","date":"2023-08-11","arxiv_id":"2308.06009","repositories_listed":0,"syntology":null},{"url":null,"slug":"g2l-semantically-aligned-and-uniform-video","title":"G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory","date":"2023-07-26","arxiv_id":"2307.14277","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-frills-temporal-video-grounding-multi","title":"No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection","date":"2023-07-20","arxiv_id":"2307.10567","repositories_listed":0,"syntology":null},{"url":null,"slug":"generation-guided-multi-level-unified-network","title":"Generation-Guided Multi-Level Unified Network for Video Grounding","date":"2023-03-14","arxiv_id":"2303.07748","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-templated-caption-for-video","title":"Exploiting Auxiliary Caption for Video Grounding","date":"2023-01-15","arxiv_id":"2301.05997","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-static-and-dynamic-vision","title":"Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-semantic-correspondence-networks","title":"Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-proposal-refinement-for-weakly","title":"Iterative Proposal Refinement for Weakly-Supervised Video Grounding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"winner-weakly-supervised-hierarchical","title":"WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-free-training-for-zero-shot-video","title":"Language-free Training for Zero-shot Video Grounding","date":"2022-10-24","arxiv_id":"2210.12977","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph2vid-flow-graph-to-video-grounding","title":"Graph2Vid: Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization","date":"2022-10-10","arxiv_id":"2210.04996","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effects-of-video-grounding-on-language","title":"On the Effects of Video Grounding on Language Models","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-feature-diversity-for-make-up","title":"Exploiting Feature Diversity for Make-up Temporal Video Grounding","date":"2022-08-12","arxiv_id":"2208.06179","repositories_listed":0,"syntology":null},{"url":"/paper/stvgformer-spatio-temporal-video-grounding","slug":"stvgformer-spatio-temporal-video-grounding","title":"STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding","date":"2022-07-06","arxiv_id":"2207.02756","repositories_listed":0,"syntology":null},{"url":null,"slug":"team-pku-wict-mipl-pic-makeup-temporal-video","title":"Team PKU-WICT-MIPL PIC Makeup Temporal Video Grounding Challenge 2022 Technical Report","date":"2022-07-06","arxiv_id":"2207.02687","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-kernel-based-cross-modal-network-for","title":"Gaussian Kernel-based Cross Modal Network for Spatio-Temporal Video Grounding","date":"2022-07-02","arxiv_id":"2207.00744","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-aware-location-regression-network","title":"Position-aware Location Regression Network for Temporal Video Grounding","date":"2022-04-12","arxiv_id":"2204.05499","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-modeling-via-information-tree-for","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","date":"2022-03-15","arxiv_id":"2203.08013","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-self-contrastive-learning-with","title":"Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding","date":"2022-03-08","arxiv_id":"2203.03838","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-temporal-video-grounding-with","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","date":"2022-01-14","arxiv_id":"2201.05307","repositories_listed":0,"syntology":null}],"syntology_records":24,"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":23,"papers_where_code_ran_first_page":"/task/video-grounding/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/video-grounding/papers/2","json":"/task/video-grounding/papers/2.json","rows":14},{"order":"ran","page":1,"of":1,"url":"/task/video-grounding/papers/ran/1","json":"/task/video-grounding/papers/ran/1.json","rows":23}],"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":"9489956b10859362b76f41124f6ab98a59becefca7da609dcb95687049501d54","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}