{"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/spatio-temporal-video-grounding","name":"Spatio-Temporal Video Grounding","slug":"spatio-temporal-video-grounding","description_markdown":"Spatio-temporal video grounding is a computer vision and natural language processing (NLP) task that involves linking textual descriptions to specific spatio-temporal regions or moments in a video. In other words, it aims to determine which parts of a video correspond to a given textual query or description. This task is essential for various applications, including video summarization, content-based video retrieval, video captioning, and more.","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":22,"papers_with_code":10,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/spatio-temporal-video-grounding-on-hc-stvg2","slug":"spatio-temporal-video-grounding-on-hc-stvg2","dataset":"HC-STVG2","dataset_url":"/dataset/hc-stvg2","rows_in_archive":4,"metrics":["Val m_vIoU","Val vIoU@0.3","Val vIoU@0.5"],"first_row_in_archive_order":{"model":"TA-STVG","paper_title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","paper_url":"/paper/knowing-your-target-target-aware-transformer","paper_date":"2025-02-16","arxiv_id":"2502.11168","code_links":[{"title":"HengLan/TA-STVG","url":"https://github.com/HengLan/TA-STVG"}],"syntology":null}},{"leaderboard":"/sota/spatio-temporal-video-grounding-on-hc-stvg1","slug":"spatio-temporal-video-grounding-on-hc-stvg1","dataset":"HC-STVG1","dataset_url":"/dataset/hc-stvg1","rows_in_archive":3,"metrics":["m_vIoU","vIoU@0.3","vIoU@0.5"],"first_row_in_archive_order":{"model":"TA-STVG","paper_title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","paper_url":"/paper/knowing-your-target-target-aware-transformer","paper_date":"2025-02-16","arxiv_id":"2502.11168","code_links":[{"title":"HengLan/TA-STVG","url":"https://github.com/HengLan/TA-STVG"}],"syntology":null}},{"leaderboard":"/sota/spatio-temporal-video-grounding-on-vidstg","slug":"spatio-temporal-video-grounding-on-vidstg","dataset":"VidSTG","dataset_url":"/dataset/vidstg","rows_in_archive":3,"metrics":["Declarative m_vIoU","Declarative vIoU@0.3","Declarative vIoU@0.5","Interrogative m_vIoU","Interrogative vIoU@0.3","Interrogative vIoU@0.5"],"first_row_in_archive_order":{"model":"TA-STVG","paper_title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","paper_url":"/paper/knowing-your-target-target-aware-transformer","paper_date":"2025-02-16","arxiv_id":"2502.11168","code_links":[{"title":"HengLan/TA-STVG","url":"https://github.com/HengLan/TA-STVG"}],"syntology":null}}],"datasets":[{"url":"/dataset/vidstg","name":"VidSTG","full_name":"","num_papers_in_archive":29},{"url":"/dataset/hc-stvg2","name":"HC-STVG2","full_name":"","num_papers_in_archive":5},{"url":"/dataset/hc-stvg1","name":"HC-STVG1","full_name":"Human-centric Spatio-Temporal Video Grounding","num_papers_in_archive":4}],"subtasks":[],"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":1,"rows_per_page":100,"shown":22,"of":22,"of_with_code":10,"tagged_in_all":22,"counts":{"archive_papers_tagged":22,"with_a_code_link":10,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/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/large-scale-pre-training-for-grounded-video","slug":"large-scale-pre-training-for-grounded-video","title":"Large-scale Pre-training for Grounded Video Caption Generation","date":"2025-03-13","arxiv_id":"2503.10781","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/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/guided-attention-for-interpretable-motion","slug":"guided-attention-for-interpretable-motion","title":"Guided Attention for Interpretable Motion Captioning","date":"2023-10-11","arxiv_id":"2310.07324","repositories_listed":1,"syntology":null},{"url":"/paper/what-when-and-where-self-supervised-spatio","slug":"what-when-and-where-self-supervised-spatio","title":"What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions","date":"2023-03-29","arxiv_id":"2303.16990","repositories_listed":1,"syntology":null},{"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/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/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/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":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":"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":"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":"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":"/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":"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":"augmented-2d-tan-a-two-stage-approach-for","title":"Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding","date":"2021-06-20","arxiv_id":"2106.10634","repositories_listed":0,"syntology":null},{"url":null,"slug":"stvgbert-a-visual-linguistic-transformer","title":"STVGBert: A Visual-Linguistic Transformer Based Framework for Spatio-Temporal Video Grounding","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"object-aware-multi-branch-relation-networks","title":"Object-Aware Multi-Branch Relation Networks for Spatio-Temporal Video Grounding","date":"2020-08-16","arxiv_id":"2008.06941","repositories_listed":0,"syntology":null}],"syntology_records":5,"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":5,"papers_where_code_ran_first_page":"/task/spatio-temporal-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":"ran","page":1,"of":1,"url":"/task/spatio-temporal-video-grounding/papers/ran/1","json":"/task/spatio-temporal-video-grounding/papers/ran/1.json","rows":5}],"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":"4d8661a9c718c332cadfe9fc37fcfa4eaf968ccacd3f6f96a25fc0989bfc899d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}