{"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/moment-retrieval/papers/2","list_of":"/task/moment-retrieval","task":"Moment Retrieval","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":[101,132],"of":132,"counts":{"archive_papers_tagged":132,"with_a_code_link":76,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":132,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/moment-retrieval","prev":"/task/moment-retrieval","next":null,"papers":[{"url":null,"slug":"generative-video-diffusion-for-unseen-cross","title":"Generative Video Diffusion for Unseen Cross-Domain Video Moment Retrieval","date":"2024-01-24","arxiv_id":"2401.13329","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-generative-language-models-for","title":"Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning","date":"2023-12-10","arxiv_id":"2312.06699","repositories_listed":0,"syntology":null},{"url":null,"slug":"scanet-scene-complexity-aware-network-for-1","title":"SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval","date":"2023-10-08","arxiv_id":"2310.05241","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":"a-survey-on-video-moment-localization","title":"A Survey on Video Moment Localization","date":"2023-06-13","arxiv_id":"2306.07515","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-video-moment-retrieval-with-point","title":"Faster Video Moment Retrieval with Point-Level Supervision","date":"2023-05-23","arxiv_id":"2305.14017","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-generalisable-video-moment-retrieval","title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training","date":"2023-02-28","arxiv_id":"2303.00040","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-video-corpus-moment-retrieval","title":"Interactive Video Corpus Moment Retrieval using Reinforcement Learning","date":"2023-02-19","arxiv_id":"2302.09522","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-video-moment-ranking-with-multimodal","title":"Multi-video Moment Ranking with Multimodal Clue","date":"2023-01-29","arxiv_id":"2301.13606","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-perceiving-video-language-pre","title":"Temporal Perceiving Video-Language Pre-training","date":"2023-01-18","arxiv_id":"2301.07463","repositories_listed":0,"syntology":null},{"url":"/paper/simvtp-simple-video-text-pre-training-with","slug":"simvtp-simple-video-text-pre-training-with","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","date":"2022-12-07","arxiv_id":"2212.03490","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-video-moment-retrieval-with-off-the","title":"Zero-shot Video Moment Retrieval With Off-the-Shelf Models","date":"2022-11-03","arxiv_id":"2211.02178","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedvmr-a-new-federated-learning-method-for","title":"FedVMR: A New Federated Learning method for Video Moment Retrieval","date":"2022-10-28","arxiv_id":"2210.15977","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-cross-domain-alignment-network","title":"Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval","date":"2022-09-23","arxiv_id":"2209.11572","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-cross-modal-consolidation-for","title":"Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"axiou-an-axiomatically-justified-measure-for","title":"AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval","date":"2022-03-30","arxiv_id":"2203.16062","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-elements-of-temporal-sentence-grounding","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","date":"2022-01-20","arxiv_id":"2201.08071","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-2d-representation-learning-for","title":"Multi-scale 2D Representation Learning for weakly-supervised moment retrieval","date":"2021-11-04","arxiv_id":"2111.02741","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-video-retrieval-before-moment","title":"Coarse to Fine: Video Retrieval before Moment Localization","date":"2021-10-14","arxiv_id":"2110.07201","repositories_listed":0,"syntology":null},{"url":null,"slug":"viseret-a-simple-yet-effective-approach-to","title":"ViSeRet: A simple yet effective approach to moment retrieval via fine-grained video segmentation","date":"2021-10-11","arxiv_id":"2110.05146","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-moment-retrieval-with-text-query","title":"Video Moment Retrieval with Text Query Considering Many-to-Many Correspondence Using Potentially Relevant Pair","date":"2021-06-25","arxiv_id":"2106.13566","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-relational-graph-for-cross-modal","title":"Multi-Modal Relational Graph for Cross-Modal Video Moment Retrieval","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-video-moment-retrieval","title":"Fast Video Moment Retrieval","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-moment-retrieval-via-natural-language","title":"Video Moment Retrieval via Natural Language Queries","date":"2020-09-04","arxiv_id":"2009.02406","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-based-localization-of-moments-in-a-video","title":"Text-based Localization of Moments in a Video Corpus","date":"2020-08-20","arxiv_id":"2008.08716","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-adjacency-matrix-for-video-query","title":"Generating Adjacency Matrix for Video Relocalization","date":"2020-08-19","arxiv_id":"2008.08977","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-network-for-video-query-based","title":"Graph Neural Network for Video Relocalization","date":"2020-07-20","arxiv_id":"2007.09877","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-networks-for-cross-modal","title":"Language Guided Networks for Cross-modal Moment Retrieval","date":"2020-06-18","arxiv_id":"2006.10457","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-video-moment-retrieval-via","title":"Weakly-Supervised Video Moment Retrieval via Semantic Completion Network","date":"2019-11-19","arxiv_id":"1911.08199","repositories_listed":0,"syntology":null},{"url":null,"slug":"wman-weakly-supervised-moment-alignment-1","title":"LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval","date":"2019-09-27","arxiv_id":"1909.13784","repositories_listed":0,"syntology":null},{"url":null,"slug":"wman-weakly-supervised-moment-alignment","title":"wMAN: WEAKLY-SUPERVISED MOMENT ALIGNMENT NETWORK FOR TEXT-BASED VIDEO SEGMENT RETRIEVAL","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"man-moment-alignment-network-for-natural","title":"MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment","date":"2018-11-30","arxiv_id":"1812.00087","repositories_listed":0,"syntology":null}],"record_sha256":"a22a58aeb2156215f14638829d74b19c1e3cfb7d1e5cbfc0a9555293dfdad147","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}