{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:50:31Z","timestamp":1776145831880,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government [Ministry of Science and ICT (MSIT)]"},{"name":"[Artificial Intelligence Graduate School Program (Hanyang University)]","award":["RS-2020-II201373"],"award-info":[{"award-number":["RS-2020-II201373"]}]},{"name":"IITP Grant funded by Korean Government (MSIT)","award":["RS-2025-02219062"],"award-info":[{"award-number":["RS-2025-02219062"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3680911","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:57:43Z","timestamp":1775505463000},"page":"54442-54453","source":"Crossref","is-referenced-by-count":0,"title":["Cap4Bridge: Caption-Guided Cross-Modal Contextualization With Stochastic Augmentation for Text-Video Retrieval"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9577-7400","authenticated-orcid":false,"given":"Minju","family":"Jeon","sequence":"first","affiliation":[{"name":"Department of Data Science, Hanyang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyungee","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Data Science, Hanyang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si-Woo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Data Science, Hanyang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngtaek","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soeun","family":"Lee","sequence":"additional","affiliation":[{"name":"AI Research and Development Division, CJ Group, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7231-7494","authenticated-orcid":false,"given":"Dong-Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Data Science, Hanyang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"ref4","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021","journal-title":"arXiv:2109.04290"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref6","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language representation alignment","author":"Xue","year":"2022","journal-title":"arXiv:2209.06430"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1062"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02242"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_18"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754714"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730066"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1153"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1308"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref23","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tsimpoukelli"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref29","article-title":"CLIP2Video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref30","article-title":"CLIP2TV: Align, match and distill for video-text retrieval","author":"Gao","year":"2021","journal-title":"arXiv:2111.05610"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref32","article-title":"Tokenflow: Rethinking fine-grained cross-modal alignment in vision-language retrieval","author":"Zou","year":"2022","journal-title":"arXiv:2209.13822"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref36","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv:2111.07783"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref38","article-title":"Word representations via Gaussian embedding","author":"Vilnis","year":"2014","journal-title":"arXiv:1412.6623"},{"key":"ref39","article-title":"Modeling uncertainty with hedged instance embedding","author":"Oh","year":"2018","journal-title":"arXiv:1810.00319"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_22"},{"key":"ref41","article-title":"Disentangled representation learning for text-video retrieval","author":"Wang","year":"2022","journal-title":"arXiv:2203.07111"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_5"},{"key":"ref43","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lu"},{"key":"ref44","first-page":"6553","article-title":"A second look at exponential and cosine step sizes: Simplicity, adaptivity, and performance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02440"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0127"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref49","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref53","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019","journal-title":"arXiv:1907.13487"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3122865.3122867"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref56","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32454"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01107"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11474843.pdf?arnumber=11474843","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:05:06Z","timestamp":1776143106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11474843\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3680911","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}