{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T22:20:34Z","timestamp":1773526834654,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976067"],"award-info":[{"award-number":["61976067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10044-024-01317-5","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:03:07Z","timestamp":1722945787000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Attention-based supervised contrastive learning on fine-grained image classification"],"prefix":"10.1007","volume":"27","author":[{"given":"Qian","family":"Li","sequence":"first","affiliation":[]},{"given":"Weining","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,6]]},"reference":[{"key":"1317_CR1","doi-asserted-by":"crossref","unstructured":"Branson S, Van\u00a0Horn G, Belongie S, Perona P (2014) Bird species categorization using pose normalized deep convolutional nets. arXiv preprint arXiv:1406.2952","DOI":"10.5244\/C.28.87"},{"key":"1317_CR2","doi-asserted-by":"crossref","unstructured":"Zhang X, Xiong H, Zhou W, Lin W, Tian Q (2016) Picking deep filter responses for fine-grained image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1134\u20131142","DOI":"10.1109\/CVPR.2016.128"},{"key":"1317_CR3","doi-asserted-by":"crossref","unstructured":"Krause J, Jin H, Yang J, Fei-Fei L (2015) Fine-grained recognition without part annotations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5546--5555","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"1317_CR4","doi-asserted-by":"crossref","unstructured":"Lin TY, RoyChowdhury A, Maji S (2015) Bilinear cnn models for fine-grained visual recognition. In: Proceedings of the IEEE international conference on computer vision, pp 1449\u20131457","DOI":"10.1109\/ICCV.2015.170"},{"key":"1317_CR5","doi-asserted-by":"crossref","unstructured":"Nilsback ME, Zisserman A (2006) A visual vocabulary for flower classification. In: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR'06), vol 2, pp 1447\u20131454. IEEE","DOI":"10.1109\/CVPR.2006.42"},{"key":"1317_CR6","doi-asserted-by":"crossref","unstructured":"Reed S, Akata Z, Lee H, Schiele B (2016) Learning deep representations of fine-grained visual descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 49\u201358","DOI":"10.1109\/CVPR.2016.13"},{"key":"1317_CR7","doi-asserted-by":"crossref","unstructured":"Huang S, Xu Z, Tao D, Zhang Y (2016) Part-stacked cnn for fine-grained visual categorization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1173\u20131182","DOI":"10.1109\/CVPR.2016.132"},{"key":"1317_CR8","doi-asserted-by":"crossref","unstructured":"Zhang H, Xu T, Elhoseiny M, Huang X, Zhang S, Elgammal A, Metaxas D (2016) SPDA-CNN: unifying semantic part detection and abstraction for fine-grained recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1143\u20131152","DOI":"10.1109\/CVPR.2016.129"},{"key":"1317_CR9","doi-asserted-by":"crossref","unstructured":"Zhang N, Donahue J, Girshick R, Darrell T (2014) Part-based r-CNNs for fine-grained category detection. In: European conference on computer vision. Springer, pp 834\u2013849","DOI":"10.1007\/978-3-319-10590-1_54"},{"issue":"8","key":"1317_CR10","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1109\/TCSVT.2014.2380211","volume":"25","author":"J Fu","year":"2014","unstructured":"Fu J, Wang J, Rui Y, Wang XJ, Mei T, Lu H (2014) Image tag refinement with view-dependent concept representations. IEEE Trans Circuits Syst Video Technol 25(8):1409\u20131422","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"6","key":"1317_CR11","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/TMM.2017.2648498","volume":"19","author":"B Zhao","year":"2017","unstructured":"Zhao B, Wu X, Feng J, Peng Q, Yan S (2017) Diversified visual attention networks for fine-grained object classification. IEEE Trans Multimed 19(6):1245\u20131256","journal-title":"IEEE Trans Multimed"},{"key":"1317_CR12","unstructured":"Bachman P, Hjelm RD, Buchwalter W (2019) Learning representations by maximizing mutual information across views. Adv Neural Inf Process Syst 32"},{"key":"1317_CR13","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1317_CR14","doi-asserted-by":"crossref","unstructured":"Misra I, Maaten Lvd (2020) Self-supervised learning of pretext-invariant representations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6707\u20136717","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"1317_CR15","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning. PMLR, pp 1597\u20131607"},{"issue":"3","key":"1317_CR16","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"1317_CR17","doi-asserted-by":"crossref","unstructured":"Zheng H, Fu J, Mei T, Luo J (2017) Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE international conference on computer vision, pp 5209\u20135217","DOI":"10.1109\/ICCV.2017.557"},{"key":"1317_CR18","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1317_CR19","unstructured":"Jaderberg M, Simonyan K, Zisserman A et al. (2015) Spatial transformer networks. Adv Neural Inf Process Syst 28"},{"key":"1317_CR20","unstructured":"Almahairi A, Ballas N, Cooijmans T, Zheng Y, Larochelle H, Courville A (2016) Dynamic capacity networks. In: International conference on machine learning. PMLR, pp 2549\u20132558"},{"key":"1317_CR21","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS (2018) CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"1","key":"1317_CR22","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/technologies9010002","volume":"9","author":"A Jaiswal","year":"2020","unstructured":"Jaiswal A, Babu AR, Zadeh MZ, Banerjee D, Makedon F (2020) A survey on contrastive self-supervised learning. Technologies 9(1):2","journal-title":"Technologies"},{"key":"1317_CR23","doi-asserted-by":"crossref","unstructured":"Wu Z, Xiong Y, Yu SX, Lin D (2018) Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3733\u20133742","DOI":"10.1109\/CVPR.2018.00393"},{"key":"1317_CR24","doi-asserted-by":"publisher","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 9726\u20139735. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00975","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1317_CR25","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla P, Teterwak P, Wang C, Sarna A, Tian Y, Isola P, Maschinot A, Liu C, Krishnan D (2020) Supervised contrastive learning. Adv Neural Inf Process Syst 33:18661\u201318673","journal-title":"Adv Neural Inf Process Syst"},{"key":"1317_CR26","unstructured":"Liu S, Zhi S, Johns E, Davison AJ (2021) Bootstrapping semantic segmentation with regional contrast. arXiv preprint arXiv:2104.04465"},{"key":"1317_CR27","unstructured":"Kang B, Li Y, Xie S, Yuan Z, Feng J (2020) Exploring balanced feature spaces for representation learning. In: International conference on learning representations"},{"key":"1317_CR28","doi-asserted-by":"crossref","unstructured":"Woznia M, Silka J, Wieczorek M (2021) Deep learning based crowd counting model for drone assisted systems. In: Proceedings of the 4th ACM MobiCom workshop on drone assisted wireless communications for 5G and beyond, pp 31\u201336","DOI":"10.1145\/3477090.3481054"},{"key":"1317_CR29","doi-asserted-by":"crossref","unstructured":"Wozniak M, Wieczorek M, Silka J (2022) Deep learning based crowd counting model for drone assisted systems. In: Proceedings of the 4th ACM MobiCom workshop on drone assisted wireless communications for 5G and beyond, pp 121\u2013126","DOI":"10.1145\/3477090.3481054"},{"key":"1317_CR30","doi-asserted-by":"publisher","first-page":"15297","DOI":"10.1007\/s11042-019-7162-y","volume":"79","author":"A Vijayalakshmi","year":"2020","unstructured":"Vijayalakshmi A, Rajesh Kanna B (2020) Deep learning approach to detect malaria from microscopic images. Multimed Tools Appl 79:15297\u201315317","journal-title":"Multimed Tools Appl"},{"key":"1317_CR31","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv:1503.02531"},{"key":"1317_CR32","doi-asserted-by":"crossref","unstructured":"Wu Z, Xiong Y, Yu SX, Lin D (2018) Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 3733\u20133742","DOI":"10.1109\/CVPR.2018.00393"},{"key":"1317_CR33","unstructured":"Welinder P, Branson S, Mita T, Wah C, Schroff F, Belongie S, Perona P (2010) Caltech-ucsd birds 200"},{"key":"1317_CR34","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Fei-Fei L (2013) 3d object representations for fine-grained categorization. In: Proceedings of the IEEE international conference on computer vision workshops, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"1317_CR35","unstructured":"Maji S, Rahtu E, Kannala J, Blaschko M, Vedaldi A (2013) Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151"},{"key":"1317_CR36","unstructured":"Chen X, Fan H, Girshick RB, He K (2020) Improved baselines with momentum contrastive learning. arXiv:2003.04297"},{"key":"1317_CR37","unstructured":"Grill JB, Strub F, Altch\u00e9 F, Tallec C, Richemond PH, Buchatskaya E, Doersch C, Pires BA, Guo ZD, Azar MG, Piot B, Kavukcuoglu K, Munos R, Valko M (2020) Bootstrap your own latent a new approach to self-supervised learning. In: Proceedings of the 34th international conference on neural information processing systems. NIPS\u201920, Curran Associates Inc., Red Hook, NY, USA"},{"key":"1317_CR38","unstructured":"Wu D, Li S, Zang Z, Li SZ (2022) Exploring localization for self-supervised fine-grained contrastive learning. In: Proceedings of 33rd British machine vision conference"},{"key":"1317_CR39","unstructured":"Wu D, Li S, Zang Z, Wang K, Shang L, Sun B, Li H, Li SZ (2021) Align yourself: self-supervised pre-training for fine-grained recognition via saliency alignment. arXiv preprint arXiv:2106.15788"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-024-01317-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-024-01317-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-024-01317-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T18:15:43Z","timestamp":1726164943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-024-01317-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,6]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["1317"],"URL":"https:\/\/doi.org\/10.1007\/s10044-024-01317-5","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,6]]},"assertion":[{"value":"24 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We state that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"96"}}