{"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/papers/2","list_of":"/task/video-grounding","task":"Video Grounding","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,114],"of":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"},"first_page":"/task/video-grounding","prev":"/task/video-grounding","next":null,"papers":[{"url":"/paper/multi-level-representation-learning-with","slug":"multi-level-representation-learning-with","title":"Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-video-paragraph-grounding","title":"Semi-Supervised Video Paragraph Grounding With Contrastive Encoder","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"locformer-enabling-transformers-to-perform","title":"LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach","date":"2021-12-19","arxiv_id":"2112.10066","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-dense-video-grounding-via-parallel","title":"End-to-End Dense Video Grounding via Parallel Regression","date":"2021-09-23","arxiv_id":"2109.11265","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-pursuit-of-designing-multi-modal","title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","date":"2021-09-13","arxiv_id":"2109.06085","repositories_listed":0,"syntology":null},{"url":null,"slug":"evoquer-enhancing-temporal-grounding-with","title":"EVOQUER: Enhancing Temporal Grounding with Video-Pivoted BackQuery Generation","date":"2021-09-10","arxiv_id":"2109.04600","repositories_listed":0,"syntology":null},{"url":"/paper/support-set-based-cross-supervision-for-video","slug":"support-set-based-cross-supervision-for-video","title":"Support-Set Based Cross-Supervision for Video Grounding","date":"2021-08-24","arxiv_id":"2108.10576","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":"cascaded-prediction-network-via-segment-tree","title":"Cascaded Prediction Network via Segment Tree for Temporal Video Grounding","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-attention-network-with-sequence","title":"Parallel Attention Network with Sequence Matching for Video Grounding","date":"2021-05-18","arxiv_id":"2105.08481","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-grounding-networks-with-semantic-attention","title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos","date":"2021-03-23","arxiv_id":"2103.12346","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},{"url":null,"slug":"not-all-frames-are-equal-weakly-supervised","title":"Not All Frames Are Equal: Weakly-Supervised Video Grounding With Contextual Similarity and Visual Clustering Losses","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"df8b3500ae3c4f5ea0efb1ac5e6e479ce50ce3315da26be9a9b891dfe71ab94f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}