{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:32Z","timestamp":1784179112520,"version":"3.55.0"},"reference-count":118,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02252","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24297-24308","source":"Crossref","is-referenced-by-count":2,"title":["Enrich and Detect: Video Temporal Grounding With Multimodal Llms"],"prefix":"10.1109","author":[{"given":"Shraman","family":"Pramanick","sequence":"first","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Effrosyni","family":"Mavroudi","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yale","family":"Song","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rama","family":"Chellappa","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Torresani","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Triantafyllos","family":"Afouras","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3522295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2188"},{"key":"ref3","first-page":"561","article-title":"Support vector machines for multiple-instance learning","author":"Andrews","year":"2003","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16175"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref8","first-page":"28442","article-title":"End-to-end multi-modal video temporal grounding","volume":"34","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2535231"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1091"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.60"},{"key":"ref16","first-page":"1984","article-title":"Excl: Extractive clip localization using natural language descriptions","author":"Ghosh","year":"2019","journal-title":"NAACL"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"ref18","article-title":"Saliency-guided detr for moment retrieval and highlight detection","author":"Gordeev","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref20","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_41"},{"key":"ref25","article-title":"Multi-modal dense video captioning","volume-title":"CVPR Workshops","author":"Iashin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00250"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.294"},{"key":"ref28","first-page":"2539","article-title":"Language-free training for zeroshot video grounding","author":"Kim","year":"2023","journal-title":"WACV"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"ref32","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"NeurIPS"},{"key":"ref33","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2025","journal-title":"TMLR"},{"key":"ref34","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2880"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref40","first-page":"2794","article-title":"Univtg: Towards unified videolanguage temporal grounding","author":"Lin","year":"2023","journal-title":"ICCV"},{"key":"ref41","first-page":"11235","article-title":"Contextaware biaffine localizing network for temporal sentence grounding","author":"Liu","year":"2021","journal-title":"CVPR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref44","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","journal-title":"ICLR"},{"key":"ref45","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3228167"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3796716"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00297"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01395"},{"key":"ref51","article-title":"Visual classification via description from large language models","author":"Menon","year":"2023","journal-title":"ICLR"},{"key":"ref52","article-title":"Correlation-guided query-dependency calibration for video temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01082"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_24"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414640"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref62","article-title":"Rephrase, augment, reason: Visual grounding of questions for vision-language models","author":"Prasad","year":"2024","journal-title":"ICLR"},{"key":"ref63","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024","journal-title":"ICML"},{"key":"ref64","first-page":"119336","article-title":"Streaming long video understanding with large language models","volume":"37","author":"Qian","year":"2024","journal-title":"NeurIPS"},{"key":"ref65","article-title":"Questionanswering dense video events","author":"Qin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00112"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.140"},{"key":"ref77","first-page":"2980","article-title":"and GKHP Doll\u00e1r. Focal loss for dense object detection","author":"Ross","year":"2017","journal-title":"CVPR"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref81","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01288"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00145"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.50"},{"key":"ref86","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref87","article-title":"Hawkeye: Training video-text 11 ms for grounding text in videos","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01769"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref92","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","author":"Yang","year":"2022","journal-title":"NeurIPS"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref94","article-title":"Self-chained image-language model for video localization and question answering","volume":"36","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3475723.3484247"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02208"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref99","article-title":"Timesuite: Improving mllms for long video understanding via grounded tuning","author":"Zeng","year":"2025","journal-title":"ICLR"},{"key":"ref100","first-page":"21715","article-title":"A simple 11m framework for long-range video question-answering","author":"Zhang","year":"2024","journal-title":"EMNLP"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref114","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref116","article-title":"End-to-end dense video captioning as sequence generation","volume":"abs\/2204.08121","author":"Zhu","year":"2022","journal-title":"ArXiv"},{"key":"ref117","first-page":"5651","article-title":"End-to-end dense video captioning as sequence generation","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Zhu"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00365"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444548.pdf?arnumber=11444548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:53Z","timestamp":1777613393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":118,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02252","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}