{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:14:28Z","timestamp":1761894868294,"version":"build-2065373602"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209250","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Attribute-Guided Zero-Shot CLIP in Image Classification"],"prefix":"10.1109","author":[{"given":"Guoxi","family":"Qiu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghua","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TIP.2024.3473532"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TIP.2021.3084354"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR52729.2023.02277"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TPAMI.2021.3088859"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref6","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML.","author":"Li","year":"2022"},{"key":"ref7","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML.","author":"Jia","year":"2021"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML.","author":"Radford","year":"2021"},{"key":"ref9","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML.","author":"Chen","year":"2020"},{"key":"ref10","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML.","author":"Li","year":"2023"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/978-3-030-58577-8_7"},{"year":"2019","author":"Li","article-title":"Visualbert: A simple and performant baseline for vision and language","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/s11263-022-01653-1"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR52688.2022.01631"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1007\/978-3-031-19827-4_41"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR52729.2023.01832"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/s11263-023-01891-x"},{"year":"2022","author":"Zhang","article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","key":"ref18"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1609\/aaai.v37i1.25152"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"ref21","first-page":"26342","article-title":"Chils: Zero-shot image classification with hierarchical label sets","volume-title":"ICML.","author":"Novack","year":"2023"},{"year":"2022","author":"Menon","article-title":"Visual classification via description from large language models","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref24","article-title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories","author":"Fei-Fei","year":"2004","journal-title":"CVPR-w"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR.2012.6248092"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICCVW.2013.77"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICVGIP.2008.47"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1007\/978-3-319-10599-4_29"},{"year":"2013","author":"Maji","article-title":"Fine-grained visual classification of aircraft","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR.2010.5539970"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/CVPR.2014.461"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/JSTARS.2019.2918242"},{"year":"2012","author":"Soomro","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","key":"ref33"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR.2009.5206772"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209250.pdf?arnumber=11209250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:37:56Z","timestamp":1761889076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209250","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}