{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:55:21Z","timestamp":1788879321017,"version":"build-2803163510"},"reference-count":69,"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\/iccv51701.2025.02023","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21789-21799","source":"Crossref","is-referenced-by-count":3,"title":["Prototypes Are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval"],"prefix":"10.1109","author":[{"given":"WonJun","family":"Moon","sequence":"first","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheol-Ho","family":"Cho","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Woojin","family":"Jun","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taeoh","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inwoong","family":"Lee","sequence":"additional","affiliation":[{"name":"NAVER Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyoon","family":"Wee","sequence":"additional","affiliation":[{"name":"NAVER Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minho","family":"Shim","sequence":"additional","affiliation":[{"name":"NAVER Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae-Pil","family":"Heo","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00338"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28389"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00957"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3257193"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01622"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00264"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2801"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00379"},{"key":"ref23","article-title":"Prototype-based aleatoric uncertainty quantification for cross-modal retrieval","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00361"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350879"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref38","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref41","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658088"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01248"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32252"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32437"},{"key":"ref49","article-title":"Large-scale vision-language models learn super images for efficient and high-performance partially relevant video retrieval","author":"Nishimura","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_21"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00526"},{"key":"ref54","first-page":"19730","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref56","article-title":"Making llama see and draw with seed tokenizer","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ge"},{"key":"ref57","first-page":"11525","article-title":"Object-centric learning with slot attention","volume":"33","author":"Locatello","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref58","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"In International conference on machine learning","author":"Jaegle"},{"key":"ref59","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"In International conference on machine learning","author":"Chen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105168"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref64","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":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"}],"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\/11445299.pdf?arnumber=11445299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:33Z","timestamp":1777611333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445299\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02023","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}