{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:19Z","timestamp":1777889719572,"version":"3.51.4"},"reference-count":58,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306067,62220106008"],"award-info":[{"award-number":["62306067,62220106008"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.02164","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23311-23320","source":"Crossref","is-referenced-by-count":0,"title":["KDA: Knowledge Diffusion Alignment with Enhanced Context for Video Temporal Grounding"],"prefix":"10.1109","author":[{"given":"Ran","family":"Ran","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Jiwei","family":"Wei","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Shiyuan","family":"He","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Zeyu","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Chaoning","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Ning","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref7","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","volume":"33","author":"Ho","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3211850"},{"key":"ref12","first-page":"7249","article-title":"Prior knowledge integration via 11 m encoding and pseudo event regulation for video moment retrieval","volume-title":"ACM MM","author":"Jiang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref14","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref15","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"NeurIPS","volume":"34","author":"Lei","year":"2021"},{"key":"ref16","first-page":"12032","article-title":"G21: Semantically aligned and uniform video grounding via geodesic and game theory","volume-title":"ICCV","author":"Li","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2880"},{"key":"ref19","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"NeurIPS","volume":"35","author":"Liang","year":"2022"},{"key":"ref20","first-page":"2794","article-title":"Univtg: Towards unified videolanguage temporal grounding","volume-title":"ICCV","author":"Qinghong Lin","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref23","first-page":"5461","article-title":"Conditional video diffusion network for fine-grained temporal sentence grounding","volume":"26","author":"Liu","year":"2023","journal-title":"IEEE TMM"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref25","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","volume-title":"ICLR","author":"Liu","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref27","first-page":"421","article-title":"R 2-tuning: Efficient image-to-video transfer learning for video temporal grounding","volume-title":"ECCV","author":"Liu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32624"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00297"},{"key":"ref32","author":"Moon","year":"2023","journal-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01082"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32717"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_24"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref40","author":"Simonyan","year":"2014","journal-title":"Very deep convolutional networks for large-scale image recognition"},{"key":"ref41","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref42","first-page":"4998","article-title":"Trdetr: Task-reciprocal transformer for joint moment retrieval and highlight detection","volume-title":"AAAI","author":"Sun","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532083"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475451"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01733"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3461721"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01248"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3516033"}],"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\/11445495.pdf?arnumber=11445495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:17:46Z","timestamp":1777612666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445495\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02164","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}