{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:43:37Z","timestamp":1777059817941,"version":"3.51.4"},"reference-count":101,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":["62006200"],"award-info":[{"award-number":["62006200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2022YFG0179"],"award-info":[{"award-number":["2022YFG0179"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011172","name":"Open Fund of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation","doi-asserted-by":"publisher","award":["PLC20211104"],"award-info":[{"award-number":["PLC20211104"]}],"id":[{"id":"10.13039\/501100011172","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Cooperation Project of the China National Petroleum Corporation-Southwest Petroleum University (CNPC-SWPU) Innovation Alliance","award":["2020CX020000"],"award-info":[{"award-number":["2020CX020000"]}]},{"name":"Special Project for the Central Government to Guide the Development of Local Science and Technology in Sichuan Province","award":["2021ZYD0099"],"award-info":[{"award-number":["2021ZYD0099"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tcsvt.2022.3227737","type":"journal-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T18:39:30Z","timestamp":1670524770000},"page":"2798-2812","source":"Crossref","is-referenced-by-count":28,"title":["Fine-Grained Visual Categorization: A Spatial\u2013Frequency Feature Fusion Perspective"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5809-5327","authenticated-orcid":false,"given":"Min","family":"Wang","sequence":"first","affiliation":[{"name":"College of Electrical Engineering and Information, Southwest Petroleum University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering and Information, Southwest Petroleum University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"Fengcheng Operation Area of Xinjiang Oilfield Company, Xinjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3290-1036","authenticated-orcid":false,"given":"Fan","family":"Min","sequence":"additional","affiliation":[{"name":"School of Computer Science, Southwest Petroleum University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6036-4728","authenticated-orcid":false,"given":"Xizhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Big Data, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2679114"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.131"},{"key":"ref58","article-title":"ResNet strikes back: An improved training procedure in timm","author":"wightman","year":"2021","journal-title":"arXiv 2110 00476"},{"key":"ref53","author":"wah","year":"2011","journal-title":"The caltech-ucsd birds-200–2011 dataset"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.127"},{"key":"ref54","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume":"2","author":"khosla","year":"2011","journal-title":"Proc IEEE CVPR Workshop"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675376"},{"key":"ref50","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/83.597279"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00358"},{"key":"ref48","first-page":"1","article-title":"Fine-grained visual classification of aircraft","author":"maji","year":"2013","journal-title":"Proc HAL-INRIA"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"ref42","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1126\/science.1205438"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_19"},{"key":"ref43","author":"szedo","year":"2006","journal-title":"Color-space converter RGB to YCrCb"},{"key":"ref49","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","author":"wang","year":"2020","journal-title":"Proc NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11202"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.206"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2021.148870"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref5","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"branson","year":"2014","journal-title":"arXiv 1406 2952"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01305"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"3933","article-title":"Faster neural networks straight from jpeg","author":"gueguen","year":"2018","journal-title":"Proc NIPS"},{"key":"ref34","first-page":"1","article-title":"On using CNN with DCT based image data","author":"ulicny","year":"2017","journal-title":"Proc 19th Irish Mach Vis Image Process Conf (IMVIP)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3020227"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2998574"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.002"},{"key":"ref25","article-title":"Fully convolutional attention localization networks: Efficient attention localization for fine-grained recognition","author":"liu","year":"2016","journal-title":"arXiv 1603 06765"},{"key":"ref20","first-page":"1","article-title":"Maximum-entropy fine grained classification","volume":"31","author":"dubey","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301271"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref27","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6712"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3065693"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978115"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-00551-4_4"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1978-0468306-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2834480"},{"key":"ref16","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069835"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.145"},{"key":"ref95","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3017939"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00225"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.62"},{"key":"ref86","article-title":"NLP from scratch without large-scale pretraining: A simple and efficient framework","author":"yao","year":"2021","journal-title":"arXiv 2111 04130"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6882"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_19"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16255"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"ref74","article-title":"Deep metric learning and image classification with nearest neighbour Gaussian kernels","author":"meyer","year":"2017","journal-title":"arXiv 1705 09780"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"ref1","article-title":"TransFG: A transformer architecture for fine-grained recognition","author":"he","year":"2021","journal-title":"arXiv 2103 07976"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.63"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.24"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11223"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_38"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.276"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.325"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10144449\/09975796.pdf?arnumber=9975796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:55:14Z","timestamp":1687805714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9975796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":101,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3227737","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}