{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:25:04Z","timestamp":1763202304487},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T00:00:00Z","timestamp":1580342400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T00:00:00Z","timestamp":1580342400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11042-020-08666-3","type":"journal-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T07:03:07Z","timestamp":1580367787000},"page":"22867-22889","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Adversarial erasing attention for fine-grained image classification"],"prefix":"10.1007","volume":"80","author":[{"given":"Jinsheng","family":"Ji","sequence":"first","affiliation":[]},{"given":"Linfeng","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Weilin","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Huilin","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,1,30]]},"reference":[{"key":"8666_CR1","doi-asserted-by":"crossref","unstructured":"Akata Z, Reed S, Walter D, Lee H, Schiele B (2015) Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2927\u20132936","DOI":"10.1109\/CVPR.2015.7298911"},{"issue":"9","key":"8666_CR2","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1109\/TPAMI.2015.2500224","volume":"38","author":"H Azizpour","year":"2016","unstructured":"Azizpour H, Razavian AS, Sullivan J, Maki A, Carlsson S (2016) Factors of transferability for a generic convnet representation. IEEE Trans Pattern Anal Mach Intell 38(9):1790\u20131802","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8666_CR3","doi-asserted-by":"crossref","unstructured":"Berg T, Liu J, Woo Lee S, Alexander ML, Jacobs D, Belhumeur P (2014) Birdsnap: Large-scale fine-grained visual categorization of birds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2011\u20132018","DOI":"10.1109\/CVPR.2014.259"},{"key":"8666_CR4","doi-asserted-by":"crossref","unstructured":"Bourdev L, Maji S, Brox T, Malik J (2010) Detecting people using mutually consistent poselet activations. In: European conference on computer vision. Springer, pp 168\u2013181","DOI":"10.1007\/978-3-642-15567-3_13"},{"key":"8666_CR5","doi-asserted-by":"crossref","unstructured":"Branson S, Van Horn G, Belongie S, Perona P (2014) Bird species categorization using pose normalized deep convolutional nets. BMVC","DOI":"10.5244\/C.28.87"},{"key":"8666_CR6","doi-asserted-by":"crossref","unstructured":"Chai Y, Lempitsky V, Zisserman A (2013) Symbiotic segmentation and part localization for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp 321\u2013328","DOI":"10.1109\/ICCV.2013.47"},{"issue":"3","key":"8666_CR7","doi-asserted-by":"publisher","first-page":"2959","DOI":"10.1007\/s11042-017-4593-1","volume":"77","author":"YS Chang","year":"2018","unstructured":"Chang YS (2018) Fine-grained attention for image caption generation. Multimed Tools Appl 77(3):2959\u20132971","journal-title":"Multimed Tools Appl"},{"key":"8666_CR8","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: Delving deep into convolutional nets. arXiv:1405.3531","DOI":"10.5244\/C.28.6"},{"key":"8666_CR9","doi-asserted-by":"crossref","unstructured":"Dai Z, Chen M, Zhu S, Tan P (2018) Batch feature erasing for person re-identification and beyond. arXiv:1811.07130","DOI":"10.1109\/ICCV.2019.00379"},{"key":"8666_CR10","unstructured":"Darrell T, Huang C, Jia Y (2012) Beyond spatial pyramids: Receptive field learning for pooled image features. In: 2012 IEEE Conference on computer vision and pattern recognition. IEEE, pp 3370\u20133377"},{"issue":"2","key":"8666_CR11","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1109\/TIP.2016.2631887","volume":"26","author":"Z Ding","year":"2016","unstructured":"Ding Z, Fu Y (2016) Robust transfer metric learning for image classification. IEEE Trans Image Process 26(2):660\u2013670","journal-title":"IEEE Trans Image Process"},{"key":"8666_CR12","doi-asserted-by":"crossref","unstructured":"Farrell R, Oza O, Zhang N, Morariu VI, Darrell T, Davis LS (2011) Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance. In: 2011 IEEE international conference on Computer vision (ICCV). IEEE, pp 161\u2013168","DOI":"10.1109\/ICCV.2011.6126238"},{"key":"8666_CR13","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: CVPR","DOI":"10.1109\/CVPR.2017.476"},{"key":"8666_CR14","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"8666_CR15","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.patrec.2014.06.011","volume":"49","author":"PH Gosselin","year":"2014","unstructured":"Gosselin PH, Murray N, J\u00e9gou H, Perronnin F (2014) Revisiting the fisher vector for fine-grained classification. Pattern Recogn Lett 49:92\u201398","journal-title":"Pattern Recogn Lett"},{"key":"8666_CR16","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8666_CR17","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"},{"issue":"12","key":"8666_CR18","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TMM.2016.2602060","volume":"18","author":"C Huang","year":"2016","unstructured":"Huang C, He Z, Cao G, Cao W (2016) Task-driven progressive part localization for fine-grained object recognition. IEEE Trans Multimed 18(12):2372\u20132383","journal-title":"IEEE Trans Multimed"},{"key":"8666_CR19","unstructured":"Huh M, Agrawal P, Efros AA (2016) What makes imagenet good for transfer learning? arXiv:1608.08614"},{"key":"8666_CR20","doi-asserted-by":"crossref","unstructured":"Huh MH, Zhang N (2019) Feedback adversarial learning: Spatial feedback for improving generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1476\u20131485","DOI":"10.1109\/CVPR.2019.00157"},{"issue":"8","key":"8666_CR21","doi-asserted-by":"publisher","first-page":"2369","DOI":"10.1109\/TIP.2015.2423557","volume":"24","author":"A Iscen","year":"2015","unstructured":"Iscen A, Tolias G, Gosselin PH, J\u00e9gou H (2015) A comparison of dense region detectors for image search and fine-grained classification. IEEE Trans Image Process 24(8):2369\u20132381","journal-title":"IEEE Trans Image Process"},{"key":"8666_CR22","unstructured":"Khosla A, Jayadevaprakash N, Yao B, Li FF (2011) Novel dataset for fine-grained image categorization: Stanford dogs. In: CVPR Workshops, vol 2, pp 1"},{"key":"8666_CR23","doi-asserted-by":"crossref","unstructured":"Krause J, Jin H, Yang J, Fei-Fei L (2015) Fine-grained recognition without part annotations. In: 2015 IEEE conference on Computer vision and pattern recognition (CVPR). IEEE, pp 5546\u20135555","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"8666_CR24","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Fei-fei L (2013) 3d object representations for fine-grained categorization. In: 2013 IEEE international conference on Computer vision workshops (ICCVW). IEEE, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"8666_CR25","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"issue":"1","key":"8666_CR26","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/JBHI.2016.2635663","volume":"21","author":"A Kumar","year":"2016","unstructured":"Kumar A, Kim J, Lyndon D, Fulham M, Feng D (2016) An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE J Biomed Health Inf 21(1):31\u201340","journal-title":"IEEE J Biomed Health Inf"},{"key":"8666_CR27","doi-asserted-by":"crossref","unstructured":"Li J, Liang X, Wei Y, Xu T, Feng J, Yan S (2017) Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1222\u20131230","DOI":"10.1109\/CVPR.2017.211"},{"key":"8666_CR28","doi-asserted-by":"crossref","unstructured":"Lin TY, RoyChowdhury A, Maji S (2017) Bilinear convolutional neural networks for fine-grained visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2017.2723400"},{"key":"8666_CR29","doi-asserted-by":"crossref","unstructured":"Liu J, Kanazawa A, Jacobs D, Belhumeur P (2012) Dog breed classification using part localization. ECCV. pp 172\u2013185","DOI":"10.1007\/978-3-642-33718-5_13"},{"key":"8666_CR30","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"8666_CR31","unstructured":"Liu X, Xia T, Wang J, Lin Y (2016) Fully convolutional attention localization networks: Efficient attention localization for fine-grained recognition. CoRR, arXiv:1603.06765"},{"key":"8666_CR32","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"12","key":"8666_CR33","doi-asserted-by":"publisher","first-page":"15521","DOI":"10.1007\/s11042-017-5131-x","volume":"77","author":"X Lu","year":"2018","unstructured":"Lu X, Guo Y, Liu N, Wan L, Fang T (2018) Non-convex joint bilateral guided depth upsampling. Multimed Tools Appl 77(12):15521\u201315544","journal-title":"Multimed Tools Appl"},{"issue":"19","key":"8666_CR34","first-page":"1","volume":"10","author":"X Lu","year":"2019","unstructured":"Lu X, Ma C, Ni B, Yang X (2019) Adaptive region proposal with channel regularization for robust object tracking. IEEE Trans Circ Syst Video Technol 10(19):1\u201315","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"8666_CR35","doi-asserted-by":"crossref","unstructured":"Lu X, Ma C, Ni B, Yang X, Reid I, Yang MH (2018) Deep regression tracking with shrinkage loss. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 353\u2013369","DOI":"10.1007\/978-3-030-01264-9_22"},{"key":"8666_CR36","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.neucom.2019.02.021","volume":"349","author":"X Lu","year":"2019","unstructured":"Lu X, Ni B, Ma C, Yang X (2019) Learning transform-aware attentive network for object tracking. Neurocomputing 349:133\u2013144","journal-title":"Neurocomputing"},{"key":"8666_CR37","doi-asserted-by":"crossref","unstructured":"Lu X, Wang W, Ma C, Shen J, Shao L, Porikli F (2019) See more, know more: Unsupervised video object segmentation with co-attention siamese networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3623\u20133632","DOI":"10.1109\/CVPR.2019.00374"},{"key":"8666_CR38","unstructured":"Maji S, Rahtu E, Kannala J, Blaschko M, Vedaldi A (2013) Fine-grained visual classification of aircraft. arXiv:1306.5151"},{"key":"8666_CR39","doi-asserted-by":"crossref","unstructured":"Nilsback ME, Zisserman A (2008) Automated flower classification over a large number of classes. In: ICVGIP. IEEE, pp 722\u2013729","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"8666_CR40","doi-asserted-by":"crossref","unstructured":"Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1717\u20131724","DOI":"10.1109\/CVPR.2014.222"},{"key":"8666_CR41","doi-asserted-by":"crossref","unstructured":"Quattoni A, Collins M, Darrell T (2008) Transfer learning for image classification with sparse prototype representations. In: CVPR. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587637"},{"key":"8666_CR42","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"8666_CR43","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"8666_CR44","doi-asserted-by":"crossref","unstructured":"Rosenfeld A, Ullman S (2016) Visual concept recognition and localization via iterative introspection. In: Asian conference on computer vision. Springer, pp 264\u2013279","DOI":"10.1007\/978-3-319-54193-8_17"},{"issue":"5","key":"8666_CR45","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"HC Shin","year":"2016","unstructured":"Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM (2016) Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35(5):1285\u20131298","journal-title":"IEEE Trans Med Imaging"},{"key":"8666_CR46","doi-asserted-by":"crossref","unstructured":"Simon M, Rodner E (2015) Neural activation constellations: Unsupervised part model discovery with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1143\u20131151","DOI":"10.1109\/ICCV.2015.136"},{"key":"8666_CR47","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, pp 140\u2013C1556"},{"key":"8666_CR48","doi-asserted-by":"crossref","unstructured":"Singh KK, Ojha U, Lee YJ (2018) Finegan: Unsupervised hierarchical disentanglement for fine-grained object generation and discovery. arXiv:1811.11155","DOI":"10.1109\/CVPR.2019.00665"},{"issue":"13","key":"8666_CR49","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1177\/0278364911400640","volume":"30","author":"M Stark","year":"2011","unstructured":"Stark M, Krause J, Pepik B, Meger D, Little JJ, Schiele B, Koller D (2011) Fine-grained categorization for 3d scene understanding. Int J Robot Res 30 (13):1543\u20131552","journal-title":"Int J Robot Res"},{"key":"8666_CR50","doi-asserted-by":"crossref","unstructured":"Sumbul G, Cinbis RG, Aksoy S (2019) Multisource region attention network for fine-grained object recognition in remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing","DOI":"10.1109\/TGRS.2019.2894425"},{"key":"8666_CR51","doi-asserted-by":"crossref","unstructured":"Sun C, Shrivastava A, Singh S, Gupta A (2017) Revisiting unreasonable effectiveness of data in deep learning era. In: 2017 IEEE international conference on Computer vision (ICCV). IEEE, pp 843\u2013852","DOI":"10.1109\/ICCV.2017.97"},{"key":"8666_CR52","doi-asserted-by":"crossref","unstructured":"Van Horn G, Branson S, Farrell R, Haber S, Barry J, Ipeirotis P, Perona P, Belongie S (2015) Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 595\u2013604","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"8666_CR53","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset. California Inst. Technol. Pasadena, Tech. Rep CNS-TR-2011-001"},{"key":"8666_CR54","doi-asserted-by":"crossref","unstructured":"Wang D, Shen Z, Shao J, Zhang W, Xue X, Zhang Z (2015) Multiple granularity descriptors for fine-grained categorization. In: 2015 IEEE international conference on Computer vision (ICCV). IEEE, pp 2399\u20132406","DOI":"10.1109\/ICCV.2015.276"},{"key":"8666_CR55","doi-asserted-by":"crossref","unstructured":"Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X (2017) Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2017.683"},{"key":"8666_CR56","doi-asserted-by":"crossref","unstructured":"Wang H, Gong D, Li Z, Liu W (2019) Decorrelated adversarial learning for age-invariant face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3527\u20133536","DOI":"10.1109\/CVPR.2019.00364"},{"key":"8666_CR57","doi-asserted-by":"crossref","unstructured":"Wang W, Lu X, Shen J, Crandall DJ, Shao L (2019) Zero-shot video object segmentation via attentive graph neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp 9236\u20139245","DOI":"10.1109\/ICCV.2019.00933"},{"key":"8666_CR58","doi-asserted-by":"crossref","unstructured":"Wang Y, Choi J, Morariu VI, Davis LS (2016) Mining discriminative triplets of patches for fine-grained classification. arXiv:1605.01130","DOI":"10.1109\/CVPR.2016.131"},{"key":"8666_CR59","doi-asserted-by":"crossref","unstructured":"Wegner JD, Branson S, Hall D, Schindler K, Perona P (2016) Cataloging public objects using aerial and street-level images-urban trees. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6014\u20136023","DOI":"10.1109\/CVPR.2016.647"},{"key":"8666_CR60","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1016\/j.patcog.2017.10.002","volume":"76","author":"XS Wei","year":"2018","unstructured":"Wei XS, Xie CW, Wu J, Shen C (2018) Mask-cnn: Localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recogn 76:704\u2013714","journal-title":"Pattern Recogn"},{"key":"8666_CR61","doi-asserted-by":"crossref","unstructured":"Wei Y, Feng J, Liang X, Cheng MM, Zhao Y, Yan S (2017) Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1568\u20131576","DOI":"10.1109\/CVPR.2017.687"},{"key":"8666_CR62","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 842\u2013850"},{"key":"8666_CR63","doi-asserted-by":"crossref","unstructured":"Xie L, Tian Q, Hong R, Yan S, Zhang B (2013) Hierarchical part matching for fine-grained visual categorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1641\u20131648","DOI":"10.1109\/ICCV.2013.206"},{"issue":"5","key":"8666_CR64","doi-asserted-by":"publisher","first-page":"1994","DOI":"10.1109\/TIP.2014.2310117","volume":"23","author":"L Xie","year":"2014","unstructured":"Xie L, Tian Q, Wang M, Zhang B (2014) Spatial pooling of heterogeneous features for image classification. IEEE Trans Image Process 23(5):1994\u20132008","journal-title":"IEEE Trans Image Process"},{"key":"8666_CR65","unstructured":"Xie N, Lai F, Doran D, Kadav A (2019) Visual entailment: A novel task for fine-grained image understanding. arXiv:1901.06706"},{"key":"8666_CR66","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: ECCV 2018. Springer, pp 438\u2013454","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"8666_CR67","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks?. In: Advances in neural information processing systems, pp 3320\u20133328"},{"key":"8666_CR68","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"27","key":"8666_CR69","doi-asserted-by":"publisher","first-page":"6194","DOI":"10.1364\/AO.53.006194","volume":"53","author":"H Zhang","year":"2014","unstructured":"Zhang H, Hu S, Zhang X (2014) Sift flow for large-displacement object tracking. Appl Opt 53(27):6194\u20136205","journal-title":"Appl Opt"},{"key":"8666_CR70","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.neucom.2017.04.024","volume":"249","author":"H Zhang","year":"2017","unstructured":"Zhang H, Wang Y, Luo L, Lu X, Zhang M (2017) Sift flow for abrupt motion tracking via adaptive samples selection with sparse representation. Neurocomputing 249:253\u2013265","journal-title":"Neurocomputing"},{"key":"8666_CR71","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"},{"key":"8666_CR72","unstructured":"Zhang N, Farrell R, Darrell T (2012) Pose pooling kernels for sub-category recognition. In: Computer vision and pattern recognition (CVPR), 2012 IEEE conference on, pp 3665\u20133672. IEEE"},{"key":"8666_CR73","doi-asserted-by":"crossref","unstructured":"Zhang N, Farrell R, Iandola F, Darrell T (2013) Deformable part descriptors for fine-grained recognition and attribute prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp 729\u2013736","DOI":"10.1109\/ICCV.2013.96"},{"key":"8666_CR74","unstructured":"Zhang N, Shelhamer E, Gao Y, Darrell T (2015) Fine-grained pose prediction, normalization, and recognition. arXiv:1511.07063"},{"issue":"2","key":"8666_CR75","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/s11263-012-0582-z","volume":"101","author":"T Zhang","year":"2013","unstructured":"Zhang T, Ghanem B, Liu S, Ahuja N (2013) Robust visual tracking via structured multi-task sparse learning. Int J Comput Vis 101(2):367\u2013383","journal-title":"Int J Comput Vis"},{"key":"8666_CR76","doi-asserted-by":"crossref","unstructured":"Zhang X, Wei Y, Feng J, Yang Y, Huang TS (2018) Adversarial complementary learning for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1325\u20131334","DOI":"10.1109\/CVPR.2018.00144"},{"key":"8666_CR77","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: CVPR, pp 1134\u20131142","DOI":"10.1109\/CVPR.2016.128"},{"issue":"12","key":"8666_CR78","first-page":"2736","volume":"19","author":"X Zhang","year":"2017","unstructured":"Zhang X, Xiong H, Zhou W, Lin W, Tian Q (2017) Picking neural activations for fine-grained recognition. IEEE Trans Multimed 19(12):2736\u20132750","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"8666_CR79","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1109\/TIP.2016.2531289","volume":"25","author":"Y Zhang","year":"2016","unstructured":"Zhang Y, Wei XS, Wu J, Cai J, Lu J, Nguyen VA, Do MN (2016) Weakly supervised fine-grained categorization with part-based image representation. IEEE Trans Image Process 25(4):1713\u20131725","journal-title":"IEEE Trans Image Process"},{"key":"8666_CR80","doi-asserted-by":"crossref","unstructured":"Zhao B, Feng J, Wu X, Yan S (2017) A survey on deep learning-based fine-grained object classification and semantic segmentation. Int J Autom Comput","DOI":"10.1007\/s11633-017-1053-3"},{"issue":"6","key":"8666_CR81","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":"8666_CR82","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: Int. Conf. on computer vision","DOI":"10.1109\/ICCV.2017.557"},{"key":"8666_CR83","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: 2016 IEEE conference on Computer vision and pattern recognition (CVPR). IEEE, pp 2921\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\/s11042-020-08666-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-08666-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-08666-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,3]],"date-time":"2021-07-03T09:08:50Z","timestamp":1625303330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-08666-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,30]]},"references-count":83,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["8666"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-08666-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,30]]},"assertion":[{"value":"29 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}