{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:22:00Z","timestamp":1781587320470,"version":"3.54.5"},"reference-count":48,"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\/iccv51701.2025.02271","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24497-24506","source":"Crossref","is-referenced-by-count":2,"title":["Hybrid-Tower: Fine-Grained Pseudo-Query Interaction and Generation for Text-to-Video Retrieval"],"prefix":"10.1109","author":[{"given":"Bangxiang","family":"Lan","sequence":"first","affiliation":[{"name":"Renmin University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruobing","family":"Xie","sequence":"additional","affiliation":[{"name":"Tencent,Large Language Model Department"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingwu","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent,Large Language Model Department"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanhui","family":"Kang","sequence":"additional","affiliation":[{"name":"Tencent,Large Language Model Department"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Yang","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"End-toend object detection with transformers","volume-title":"ECCV","author":"Carion","year":"2020"},{"key":"ref3","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"A C L","author":"Chen","year":"2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_26"},{"key":"ref15","article-title":"Vop: Text-video cooperative prompt tuning for cross-modal retrieval","volume-title":"CVPR","author":"Huang","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02563"},{"key":"ref19","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00379"},{"key":"ref22","volume-title":"W2vv++ fully deep learning for ad-hoc video search.","author":"Li","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.3042067"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"ref25","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"BMVC","author":"Liu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref27","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"NeurIPS","author":"Lu","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"Van Den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"ref33","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"ref35","article-title":"Improved deep metric learning with multiclass n-pair loss objective","volume-title":"NeurIPS","author":"Sohn","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28327"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01622"},{"key":"ref38","article-title":"Disentangled representation learning for textvideo retrieval","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref42","article-title":"Mplug-2: A modularized multi-modal foundation model across text, image and video","volume-title":"ICML","author":"Xu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref44","article-title":"Clip-vip: Adapting pretrained image-text model to video-language alignment","volume-title":"ICLR","author":"Xue","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_18"}],"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\/11445914.pdf?arnumber=11445914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:17Z","timestamp":1777613597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02271","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}