{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T07:21:23Z","timestamp":1794036083853,"version":"4.8.0"},"reference-count":45,"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"}],"funder":[{"DOI":"10.13039\/501100003741","name":"ICREA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003741","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01998","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21515-21524","source":"Crossref","is-referenced-by-count":3,"title":["Sparse-Dense Side-Tuner for Efficient Video Temporal Grounding"],"prefix":"10.1109","author":[{"given":"David","family":"Pujol-Perich","sequence":"first","affiliation":[{"name":"Universitat de Barcelona and Computer Vision Center,Barcelona,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[{"name":"Universitat de Barcelona and Computer Vision Center,Barcelona,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Albert","family":"Clap\u00e9s","sequence":"additional","affiliation":[{"name":"Universitat de Barcelona and Computer Vision Center,Barcelona,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00894"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref7","article-title":"Saliency-guided detr for moment retrieval and highlight detection","author":"Gordeev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Unleash the potential of clip for video highlight detection","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1605.07648"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"ref15","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00262"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref20","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"$r^{2}$-tuning: Efficient image-to-video transfer learning for video temporal grounding","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref23","article-title":"Llava-mr: Large language-andvision assistant for video moment retrieval","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"The surprising effectiveness of multimodal large language models for video moment retrieval","author":"Meinardus","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref27","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1919"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00895"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01281"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0944"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref37","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403218"},{"key":"ref43","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref45","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"}],"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\/11445563.pdf?arnumber=11445563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:08Z","timestamp":1777612508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01998","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}