{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:42Z","timestamp":1740122862033,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"21-23","license":[{"start":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T00:00:00Z","timestamp":1628208000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T00:00:00Z","timestamp":1628208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002865","name":"Chongqing Science and Technology Commission","doi-asserted-by":"publisher","award":["cstc2017jcyjAX0142"],"award-info":[{"award-number":["cstc2017jcyjAX0142"]}],"id":[{"id":"10.13039\/501100002865","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002865","name":"Chongqing Science and Technology Commission","doi-asserted-by":"publisher","award":["cstc2018jcyjAX0525"],"award-info":[{"award-number":["cstc2018jcyjAX0525"]}],"id":[{"id":"10.13039\/501100002865","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004829","name":"Department of Science and Technology of Sichuan Province","doi-asserted-by":"publisher","award":["2019YFG0107"],"award-info":[{"award-number":["2019YFG0107"]}],"id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s11042-021-11314-z","type":"journal-article","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T18:03:53Z","timestamp":1628273033000},"page":"32791-32805","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Attention cutting and padding learning for fine-grained image recognition"],"prefix":"10.1007","volume":"80","author":[{"given":"Zhuo","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7003-7605","authenticated-orcid":false,"given":"Hongjian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyan","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxuan","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,6]]},"reference":[{"key":"11314_CR1","doi-asserted-by":"crossref","unstructured":"Berg T,\u00a0Liu J, Woo\u00a0Lee S, Alexander ML, Jacobs DW, Belhumeur PN (2014) Birdsnap: Large-scale fine-grained visual categorization of birds. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a02011\u20132018","DOI":"10.1109\/CVPR.2014.259"},{"key":"11314_CR2","doi-asserted-by":"crossref","unstructured":"Chen Y,\u00a0Bai Y,\u00a0Zhang W,\u00a0Mei T (2019) Destruction and construction learning for fine-grained image recognition. In Proc IEEE Conf Comput Vis Pattern Recognit 5157\u20135166","DOI":"10.1109\/CVPR.2019.00530"},{"key":"11314_CR3","doi-asserted-by":"crossref","unstructured":"Cui Y,\u00a0Song Y,\u00a0Sun C,\u00a0Howard A, Belongie S (2018) Large scale fine-grained categorization and domain-specific transfer learning. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a04109\u20134118","DOI":"10.1109\/CVPR.2018.00432"},{"key":"11314_CR4","unstructured":"Dumoulin V,\u00a0Visin F (2016) A guide to convolution arithmetic for deep learning. arXiv preprint.\u00a0arXiv: 1603.07285"},{"key":"11314_CR5","doi-asserted-by":"crossref","unstructured":"Fu J, Zheng H, Mei T (2017) Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a04438\u20134446","DOI":"10.1109\/CVPR.2017.476"},{"issue":"3","key":"11314_CR6","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/s11263-014-0713-9","volume":"110","author":"M Guillaumin","year":"2014","unstructured":"Guillaumin M, K\u00fcttel D, Ferrari V (2014) Imagenet auto-annotation with segmentation propagation. Int J Comput Vis 110(3):328\u2013348","journal-title":"Int J Comput Vis"},{"key":"11314_CR7","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a0770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11314_CR8","doi-asserted-by":"crossref","unstructured":"Huang S, Xu Z, Tao D, Zhang Y (2016) Part-stacked cnn for fine-grained visual categorization. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a01173\u20131182","DOI":"10.1109\/CVPR.2016.132"},{"key":"11314_CR9","unstructured":"Jaderberg M, Simonyan K, Zisserman A et\u00a0al (2015) Spatial transformer networks. In Adv Neural Inf Proces Syst\u00a02017\u20132025"},{"key":"11314_CR10","doi-asserted-by":"crossref","unstructured":"Krause J, Jin H, Yang J, Fei-Fei L (2015) Fine-grained recognition without part annotations. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a05546\u20135555","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"11314_CR11","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 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"11314_CR12","doi-asserted-by":"crossref","unstructured":"Kuettel D, Guillaumin M, Ferrari V (2012) Segmentation propagation in imagenet. In European Conference on Computer Vision 459\u2013473. Springer","DOI":"10.1007\/978-3-642-33786-4_34"},{"issue":"11","key":"11314_CR13","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P et al (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"11314_CR14","doi-asserted-by":"crossref","unstructured":"Li Z, Yang Y, Liu X, Zhou F, Wen S, Xu W (2017) Dynamic computational time for visual attention. In Proceedings of the IEEE International Conference on Computer Vision 1199\u20131209","DOI":"10.1109\/ICCVW.2017.145"},{"key":"11314_CR15","unstructured":"Liu X, Xia T, Wang J, Yang Y, Zhou F, Lin Y (2016) Fully convolutional attention networks for fine-grained recognition. arXiv preprint.\u00a0arXiv: 1603.06765"},{"key":"11314_CR16","unstructured":"Maji S, Rahtu E, Kannala J, Blaschko M, Vedaldi A (2013) Fine-grained visual classification of aircraft. arXiv preprint.\u00a0arXiv: 1306.5151"},{"issue":"3","key":"11314_CR17","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1109\/TIP.2017.2774041","volume":"27","author":"Y Peng","year":"2017","unstructured":"Peng Y, He X, Zhao J (2017) Object-part attention model for fine-grained image classification. IEEE Transactions on Image Processing 27(3):1487\u20131500","journal-title":"IEEE Transactions on Image Processing"},{"key":"11314_CR18","doi-asserted-by":"crossref","unstructured":"Recasens A, Kellnhofer P, Stent S, Matusik W, Torralba A (2018) Learning to zoom: a saliency-based sampling layer for neural networks. In Proceedings of the European Conference on Computer Vision (ECCV) 51\u201366","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"11314_CR19","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez P, Gonfaus JM, Cucurull G, XavierRoca F, Gonzalez J (2018) Attend and rectify: a gated attention mechanism for fine-grained recovery. In Proceedings of the European Conference on Computer Vision (ECCV) 349\u2013364","DOI":"10.1007\/978-3-030-01237-3_22"},{"issue":"3","key":"11314_CR20","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":"11314_CR21","doi-asserted-by":"crossref","unstructured":"Sun M, Yuan Y, Zhou F, Ding E (2018) Multi-attention multi-class constraint for fine-grained image recognition. In Proceedings of the European Conference on Computer Vision (ECCV) 805\u2013821","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"11314_CR22","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset"},{"key":"11314_CR23","doi-asserted-by":"crossref","unstructured":"Wang Y, Morariu VI, Davis LS (2018) Learning a discriminative filter bank within a cnn for fine-grained recognition. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a04148\u20134157","DOI":"10.1109\/CVPR.2018.00436"},{"key":"11314_CR24","unstructured":"Wei X-S, Xie C-W, Wu J (2016) Mask-cnn: Localizing parts and selecting descriptors for fine-grained image recognition. arXiv preprint\u00a0arXiv: 1605.06878"},{"key":"11314_CR25","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1016\/j.patcog.2017.10.002","volume":"76","author":"X-S Wei","year":"2018","unstructured":"Wei X-S, Xie C-W, Wu J, Shen C (2018) Mask-cnn: Localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recognit 76:704\u2013714","journal-title":"Pattern Recognit"},{"key":"11314_CR26","unstructured":"Xiao T, Xu Y, Yang K, Zhang J, Peng Y, Zhang Z (2015) The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a0842\u2013850"},{"key":"11314_CR27","doi-asserted-by":"crossref","unstructured":"Yang Z, Luo T, Wang D, Hu Z, Gao J, Wang L (2018) Learning to navigate for fine-grained classification. In Proceedings of the European Conference on Computer Vision (ECCV) 420\u2013435","DOI":"10.1007\/978-3-030-01264-9_26"},{"issue":"6","key":"11314_CR28","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 Multimedia 19(6):1245\u20131256","journal-title":"IEEE Trans Multimedia"},{"key":"11314_CR29","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 Proc IEEE Conf Comput Vis Pattern Recognit\u00a05209\u20135217","DOI":"10.1109\/ICCV.2017.557"},{"key":"11314_CR30","doi-asserted-by":"crossref","unstructured":"Zheng H, Fu J, Zha Z-J, Luo J (2019) Looking for the devil in the details: Learning trilinear attention sampling network for fine-grained image recognition. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a05012\u20135021","DOI":"10.1109\/CVPR.2019.00515"},{"key":"11314_CR31","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In Proc IEEE Conf Comput Vis Pattern Recognit\u00a02921\u20132929","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11314-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11314-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11314-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T05:18:08Z","timestamp":1633843088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11314-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,6]]},"references-count":31,"journal-issue":{"issue":"21-23","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["11314"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11314-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2021,8,6]]},"assertion":[{"value":"19 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}