{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:37:27Z","timestamp":1730266647830,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650132","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["SC-ViT: Semantic Contrast Vision Transformer for Scene Recognition"],"prefix":"10.1109","author":[{"given":"Jiahui","family":"Niu","sequence":"first","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}]},{"given":"Xin","family":"Ma","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"Inspur Academy of Science and Technology,Jinan,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1993.378155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10231-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref6"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108530"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812248"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref13","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref15","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Kim"},{"key":"ref16","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"ArXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2567076"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2986599"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2711011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107256"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/rs13030516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/rs13204143"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109061"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3197381"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-023-09512-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn54540.2023.10191605"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191605"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110725"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112371"},{"article-title":"Vision transformer adapter for dense predictions","year":"2022","author":"Chen","key":"ref34"},{"article-title":"Cooperative semantic segmentation and image restoration in adverse environmental conditions","year":"2019","author":"Xia","key":"ref35"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2511543"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2666739"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2921960"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129227"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650132.pdf?arnumber=10650132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:00:57Z","timestamp":1725944457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650132","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}