{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:26:02Z","timestamp":1778603162646,"version":"3.51.4"},"reference-count":42,"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":["62088102,U24A20325,12326608"],"award-info":[{"award-number":["62088102,U24A20325,12326608"]}],"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\/iccv51701.2025.01873","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":2,"title":["Moment Quantization for Video Temporal Grounding"],"prefix":"10.1109","author":[{"given":"Xiaolong","family":"Sun","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanping","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liushuai","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengnan","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yabing","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Hua","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref3","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume-title":"Workshop on statistical learning in computer vision, ECCV","author":"Csurka","year":"2004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref11","article-title":"Prior knowledge integration via 11 m encoding and pseudo event regulation for video moment retrieval","author":"Jiang","year":"2024","journal-title":"ACM Multimedia 2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"ref13","first-page":"11846","article-title":"Berg, and Mohit Bansal","volume":"34","author":"Lei","year":"2021","journal-title":"Detecting moments and highlights in videos via natural language queries. Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Spikemba: Multi-modal spiking saliency mamba for temporal video grounding","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00262"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_24"},{"key":"ref18","article-title":"Discrete representations strengthen vision transformer robustness","author":"Mao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Generationaugmented retrieval for open-domain question answering","author":"Mao","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/26.3776"},{"key":"ref23","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref27","article-title":"Trdetr: Task-reciprocal transformer for joint moment retrieval and highlight detection","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32766"},{"key":"ref30","article-title":"Sq-vae: Variational bayes on discrete representation with self-annealed stochastic quantization","author":"Takida","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01733"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02341"},{"key":"ref38","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00741"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"}],"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\/11444826.pdf?arnumber=11444826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:31Z","timestamp":1777612051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01873","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}