{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:26:29Z","timestamp":1766067989513,"version":"3.37.3"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62220106008","U20B2063","62102070","62306067"],"award-info":[{"award-number":["62220106008","U20B2063","62102070","62306067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Province Innovative Talent Funding Project for Postdoctoral Fellows"},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M720660"],"award-info":[{"award-number":["2022M720660"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3401006","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:39:06Z","timestamp":1715708346000},"page":"10494-10506","source":"Crossref","is-referenced-by-count":3,"title":["Set of Diverse Queries With Uncertainty Regularization for Composed Image Retrieval"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1123-6129","authenticated-orcid":false,"given":"Yahui","family":"Xu","sequence":"first","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-1742","authenticated-orcid":false,"given":"Jiwei","family":"Wei","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9714-8738","authenticated-orcid":false,"given":"Yi","family":"Bin","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National University of Singapore, Cluny Road, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Zeyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00208"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00831"},{"key":"ref3","article-title":"Improved probabilistic image-text representations","author":"Chun","year":"2023","journal-title":"arXiv:2305.18171"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235523"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991171"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2771332"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3002956"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3034981"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2968484"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"ref19","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020","journal-title":"arXiv:2007.00145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3208742"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref28","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref29","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00262"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532047"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306738"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548126"},{"key":"ref38","first-page":"1","article-title":"Modeling uncertainty with hedged instance embeddings","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Oh"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref40","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref48","first-page":"1","article-title":"Composed image retrieval with text feedback via multi-grained uncertainty regulariza","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063297"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3207228"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3322465"},{"key":"ref53","first-page":"1","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. The 10th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00565"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref58","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref59","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref60","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref61","article-title":"Modeling uncertainty with hedged instance embeddings","author":"Oh","year":"2019","journal-title":"arXiv:1810.00319"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01115"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00213"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3639469"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28479"},{"key":"ref67","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739869\/10530361.pdf?arnumber=10530361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:15:58Z","timestamp":1732666558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":67,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3401006","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}