{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T16:08:51Z","timestamp":1762445331515,"version":"3.41.2"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Tencent Data Platform"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2022.3227973","type":"journal-article","created":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T13:40:35Z","timestamp":1670593235000},"page":"122453-122463","source":"Crossref","is-referenced-by-count":8,"title":["Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions With Multi-Level Representations"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9658-5127","authenticated-orcid":false,"given":"Jie","family":"Jiang","sequence":"first","affiliation":[{"name":"Tencent Data Platform, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7700-2149","authenticated-orcid":false,"given":"Shaobo","family":"Min","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1700-4801","authenticated-orcid":false,"given":"Weijie","family":"Kong","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8230-9471","authenticated-orcid":false,"given":"Hongfa","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-7907","authenticated-orcid":false,"given":"Zhifeng","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3865-8145","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, Guangdong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref4","article-title":"Cross modal retrieval with querybank normalisation","volume-title":"arXiv:2112.12777","author":"Bogolin","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref6","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual SoftMax loss","volume-title":"arXiv:2109.04290","author":"Cheng","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref8","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref10","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","volume-title":"arXiv:2106.11097","author":"Fang","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref13","article-title":"CLIP2TV: Align, match and distill for video-text retrieval","volume-title":"arXiv:2111.05610","author":"Gao","year":"2021"},{"key":"ref14","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","volume-title":"arXiv:2004.00849","author":"Huang","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref16","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref17","article-title":"MDMMT-2: Multidomain multimodal transformer for video retrieval, one more step towards generalization","volume-title":"arXiv:2203.07086","author":"Kunitsyn","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref19","article-title":"Align and prompt: Video-and-language pre-training with entity prompts","volume-title":"arXiv:2112.09583","author":"Li","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref23","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"arXiv:1907.13487","author":"Liu","year":"2019"},{"key":"ref24","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","volume-title":"arXiv:2002.06353","author":"Luo","year":"2020"},{"key":"ref25","article-title":"CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval","volume-title":"arXiv:2104.08860","author":"Luo","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref28","article-title":"Support-set bottlenecks for video-text representation learning","author":"Patrick","year":"2020","journal-title":"arXiv:2010.02824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1312"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref34","article-title":"Disentangled representation learning for text-video retrieval","volume-title":"arXiv:2203.07111","author":"Wang","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3122865.3122867"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref39","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"arXiv:2111.07783","author":"Yao","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10820123\/09979153.pdf?arnumber=9979153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T07:46:52Z","timestamp":1753516012000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9979153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3227973","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}