{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:58:13Z","timestamp":1782835093723,"version":"3.54.5"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10223197","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"560-564","source":"Crossref","is-referenced-by-count":6,"title":["CLIP-FG:Selecting Discriminative Image Patches by Contrastive Language-Image Pre-Training for Fine-Grained Image Classification"],"prefix":"10.1109","author":[{"given":"Min","family":"Yuan","sequence":"first","affiliation":[{"name":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China,730000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningning","family":"Lv","sequence":"additional","affiliation":[{"name":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China,730000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Xie","sequence":"additional","affiliation":[{"name":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China,730000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuxiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China,730000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhan","sequence":"additional","affiliation":[{"name":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China,730000"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/c.28.87"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref9","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref10","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR workshop on fine-grained visual categorization (FGVC)","volume":"2","author":"Khosla"},{"key":"ref11","article-title":"i l. fei-fei,3d object representations for fine-grained categorization","volume-title":"u 4th international ieee workshop on 3d representation and recognition (3drr-13)","author":"Krause"},{"key":"ref12","article-title":"Maximum-entropy fine grained classification","volume":"31","author":"Dubey","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref19","article-title":"Learning deep bilinear transformation for fine-grained image representation","volume":"32","author":"Zheng","year":"2019","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10223197.pdf?arnumber=10223197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:56:49Z","timestamp":1709326609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10223197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10223197","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}