{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:08:36Z","timestamp":1784178516881,"version":"3.55.0"},"reference-count":63,"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\/iccv51701.2025.02054","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22120-22130","source":"Crossref","is-referenced-by-count":3,"title":["Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval Via Uncertainty Minimization"],"prefix":"10.1109","author":[{"given":"Bingqing","family":"Zhang","sequence":"first","affiliation":[{"name":"The University of Queensland,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Cao","sequence":"additional","affiliation":[{"name":"The University of Queensland,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heming","family":"Du","sequence":"additional","affiliation":[{"name":"The University of Queensland,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"CSIRO Data61,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Queensland,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Liu","sequence":"additional","affiliation":[{"name":"CSIRO Data61,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Queensland,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref2","article-title":"Askvideos-videoclip: Language-grounded video embeddings","year":"2024","journal-title":"GitHub"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00185"},{"key":"ref4","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL-2011)","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00859"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00320"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611756"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref16","article-title":"Clustering items from adaptively collected inconsistent feedback","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Gupta"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.41"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref19","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3227973"},{"key":"ref21","article-title":"Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Kuhn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.46"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2684"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref25","article-title":"A survey on deep active learning: Recent advances and new frontiers","volume":"abs\/2405.00334","author":"Li","year":"2024","journal-title":"CoRR"},{"key":"ref26","article-title":"Prototype-based aleatoric uncertainty quantification for cross-modal retrieval","volume":"abs\/2309.17093","author":"Li","year":"2023","journal-title":"arXiv"},{"key":"ref27","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning, ICML 2022","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00379"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2801"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","first-page":"279","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"30th British Machine Vision Conference 2019, BMVC 2019","author":"Liu","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_40"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548361"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548361"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00063-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6190099"},{"key":"ref42","volume-title":"ChatGPT","year":"2023"},{"key":"ref43","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event","author":"Patrick"},{"key":"ref44","article-title":"Granular multimodal attention networks for visual dialog","volume":"abs\/1910.05728","author":"Patro","year":"2019","journal-title":"arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/9781119994398"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-eacl.84"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/76.718510"},{"key":"ref49","volume-title":"Multitask prompted training enables zero-shot task generalization","author":"Sanh","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01109"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28327"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334430"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref55","article-title":"Clip-vip: Adapting pretrained image-text model to video-language alignment","volume-title":"International Conference on Learning Representations","author":"Xue"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612090"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00485"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729936"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758257"},{"key":"ref62","article-title":"Languagebind: Extending video-language pretraining to n modality by language-based semantic alignment","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Zhu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"}],"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\/11446322.pdf?arnumber=11446322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:51Z","timestamp":1777611531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02054","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}