{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:34:15Z","timestamp":1783636455714,"version":"3.55.0"},"reference-count":85,"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":["62206174"],"award-info":[{"award-number":["62206174"]}],"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\/iccv51701.2025.02113","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22760-22771","source":"Crossref","is-referenced-by-count":4,"title":["Sim-DETR: Unlock DETR for Temporal Sentence Grounding"],"prefix":"10.1109","author":[{"given":"Jiajin","family":"Tang","sequence":"first","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengxuan","family":"Wei","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Shi","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sibei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445463"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01636"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref16","article-title":"Excl: Extractive clip localization using natural language descriptions","author":"Ghosh","year":"2019","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"56795690","article-title":"Selfsupervised co-training for video representation learning","volume":"33","author":"Han","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1138"},{"key":"ref21","article-title":"Mvtokenflow: High-quality 4d content generation using multiview token flow","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325019"},{"key":"ref24","first-page":"8046","article-title":"Relational self-attention: What\u2019s missing in attention for video understanding","volume":"34","author":"Kim","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"ref26","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":"ref27","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","author":"Lei","year":"2021","journal-title":"Neurips"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2880"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00379"},{"key":"ref31","article-title":"Spikemba: Multi-modal spiking saliency mamba for temporal video grounding","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"2794","article-title":"Univtg: Towards unified videolanguage temporal grounding","volume-title":"ICCV","author":"Qinghong Lin","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074008"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547782"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.732"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20058"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547969"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref39","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref41","article-title":"$r^{2}$-tuning: Efficient image-to-video transfer learning for video temporal grounding","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Liu","year":"2024"},{"key":"ref42","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref44","article-title":"Generationaugmented retrieval for open-domain question answering","author":"Mao","year":"2020","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref46","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref49","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":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref51","article-title":"Sparse detr: Efficient end-to-end object detection with learnable sparsity","author":"Roh","year":"2021","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00274"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_13"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32766"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref62","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref65","article-title":"Explore-and-match: Bridging proposal-based and proposal-free with transformer for sentence grounding in videos","author":"Woo","year":"2022","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.414"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01733"},{"key":"ref72","article-title":"Entity-aware and motionaware transformers for language-driven action localization in videos","author":"Yang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref74","article-title":"Efficient detr: improving end-to-end object detector with dense prior","author":"Yao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref79","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350879"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0228"},{"key":"ref83","article-title":"Rethinking the video sampling and reasoning strategies for temporal sentence grounding","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref84","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00433"}],"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\/11443519.pdf?arnumber=11443519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:39Z","timestamp":1777529439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02113","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}