{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:08Z","timestamp":1761898028734},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687875","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Fine-Grained Scene Image Classification with Modality-Agnostic Adapter"],"prefix":"10.1109","author":[{"given":"Yiqun","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University,School of Computer Science,China"}]},{"given":"Zhao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,China"}]},{"given":"Xiangcheng","family":"Du","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,China"}]},{"given":"Xingjiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,China"}]},{"given":"Yingbin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Videt Technology,China"}]},{"given":"Cheng","family":"Jin","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,China"}]}],"member":"263","reference":[{"article-title":"Caltech-ucsd birds 200","year":"2010","author":"Welinder","key":"ref1"},{"article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"CVPR Workshops","author":"Khosla","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502197"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00458"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093373"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00407"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07617-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref11","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01630"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.42"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref16"},{"key":"ref17","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21074-8_11"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE.2018.8574624"},{"article-title":"Efficient estimation of word representations in vector space","volume-title":"International Conference on Learning Representations","author":"Mikolov","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125995"},{"article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"British Machine Vision Conference","author":"Liu","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2612829"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Ilya","key":"ref32"},{"article-title":"Sgdr: Stochastic gradient descent with warm restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref33"},{"key":"ref34","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Pytorch image models","year":"2019","author":"Wightman","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687875.pdf?arnumber=10687875","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:56:51Z","timestamp":1727762211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687875\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687875","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}