{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:42:03Z","timestamp":1780080123093,"version":"3.54.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012632","type":"print"},{"value":"9783030012649","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01264-9_26","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T04:20:53Z","timestamp":1538972453000},"page":"438-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":447,"title":["Learning to Navigate for Fine-Grained Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6299-7649","authenticated-orcid":false,"given":"Ze","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiange","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Arbelaez, P., Ponttuset, J., Barron, J., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: CVPR, pp. 328\u2013335 (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Berg, T., Belhumeur, P.N.: POOF: part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.128"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Branson, S., Horn, G.V., Belongie, S., Perona, P.: Bird species categorization using pose normalized deep convolutional nets. In: BMVC (2014)","DOI":"10.5244\/C.28.87"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Burges, C., et al.: Learning to rank using gradient descent. In: ICML, pp. 89\u201396 (2005)","DOI":"10.1145\/1102351.1102363"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Cai, S., Zuo, W., Zhang, L.: Higher-order integration of hierarchical convolutional activations for fine-grained visual categorization. In: ICCV, October 2017","DOI":"10.1109\/ICCV.2017.63"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Z., Qin, T., Liu, T.Y., Tsai, M.F., Li, H.: Learning to rank: from pairwise approach to listwise approach. In: ICML, pp. 129\u2013136 (2007)","DOI":"10.1145\/1273496.1273513"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Sminchisescu, C.: CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts. IEEE Computer Society (2012)","DOI":"10.1109\/TPAMI.2011.231"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Chai, Y., Lempitsky, V., Zisserman, A.: Symbiotic segmentation and part localization for fine-grained categorization. In: ICCV, pp. 321\u2013328 (2013)","DOI":"10.1109\/ICCV.2013.47"},{"issue":"11","key":"26_CR9","doi-asserted-by":"publisher","first-page":"5140","DOI":"10.1109\/TIT.2008.929939","volume":"54","author":"D Cossock","year":"2008","unstructured":"Cossock, D., Zhang, T.: Statistical analysis of bayes optimal subset ranking. IEEE Trans. Inf. Theory 54(11), 5140\u20135154 (2008)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"26_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/978-3-642-15555-0_42","volume-title":"Computer Vision \u2013 ECCV 2010","author":"I Endres","year":"2010","unstructured":"Endres, I., Hoiem, D.: Category independent object proposals. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 575\u2013588. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_42"},{"key":"26_CR12","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Gavves, E., Fernando, B., Snoek, C.G.M., Smeulders, A.W.M., Tuytelaars, T.: Fine-grained categorization by alignments. In: ICCV, pp. 1713\u20131720 (2014)","DOI":"10.1109\/ICCV.2013.215"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"26_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, P.H., Murray, N., Jgou, H., Perronnin, F.: Revisiting the fisher vector for fine-grained classification. Patt. Recogn. Lett. 49, 92\u201398 (2014)","journal-title":"Patt. Recogn. Lett."},{"issue":"9","key":"26_CR16","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. TPAMI 37(9), 1904\u20131916 (2015)","journal-title":"TPAMI"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Herbrich, R.: Large margin rank boundaries for ordinal regression. In: Advances in Large Margin Classifiers, vol. 88 (2000)","DOI":"10.7551\/mitpress\/1113.003.0010"},{"key":"26_CR19","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., kavukcuoglu, k.: Spatial transformer networks. In: NIPS, pp. 2017\u20132025 (2015)"},{"key":"26_CR20","unstructured":"Jie, Z., Liang, X., Feng, J., Jin, X., Lu, W., Yan, S.: Tree-structured reinforcement learning for sequential object localization. In: NIPS, pp. 127\u2013135 (2016)"},{"issue":"4","key":"26_CR21","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1137\/S0363012901385691","volume":"42","author":"VR Konda","year":"2002","unstructured":"Konda, V.R.: Actor-critic algorithms. SIAM J. Control Optim. 42(4), 1143\u20131166 (2002)","journal-title":"SIAM J. Control Optim."},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Krause, J., Jin, H., Yang, J., Fei-Fei, L.: Fine-grained recognition without part annotations. In: CVPR, June 2015","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Jia, D., Li, F.F.: 3D object representations for fine-grained categorization. In: ICCV Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"26_CR24","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Lam, M., Mahasseni, B., Todorovic, S.: Fine-grained recognition as HSnet search for informative image parts. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.688"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Li, Z., Yang, Y., Liu, X., Zhou, F., Wen, S., Xu, W.: Dynamic computational time for visual attention. In: ICCV, October 2017","DOI":"10.1109\/ICCVW.2017.145"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.106"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.170"},{"key":"26_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-642-33718-5_13","volume-title":"Computer Vision \u2013 ECCV 2012","author":"J Liu","year":"2012","unstructured":"Liu, J., Kanazawa, A., Jacobs, D., Belhumeur, P.: Dog breed classification using part localization. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 172\u2013185. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_13"},{"issue":"3","key":"26_CR30","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1561\/1500000016","volume":"3","author":"TY Liu","year":"2009","unstructured":"Liu, T.Y.: Learning to rank for information retrieval. Found. Trends Inf. Retr. 3(3), 225\u2013331 (2009)","journal-title":"Found. Trends Inf. Retr."},{"key":"26_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Liu, X., Xia, T., Wang, J., Lin, Y.: Fully convolutional attention localization networks: efficient attention localization for fine-grained recognition. CoRR (2016)","DOI":"10.1609\/aaai.v31i1.11202"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, November 2015","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"26_CR35","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. Technical report (2013)"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Moghimi, M., Belongie, S., Saberian, M., Yang, J., Vasconcelos, N., Li, L.J.: Boosted convolutional neural networks. In: BMVC, pp. 24.1\u201324.13 (2016)","DOI":"10.5244\/C.30.24"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"26_CR38","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"issue":"3","key":"26_CR39","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"26_CR40","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., Lecun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks. Arxiv (2013)"},{"issue":"2","key":"26_CR41","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154\u2013171 (2013)","journal-title":"IJCV"},{"key":"26_CR42","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report (2011)"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Wang, D., Shen, Z., Shao, J., Zhang, W., Xue, X., Zhang, Z.: Multiple granularity descriptors for fine-grained categorization. In: ICCV, pp. 2399\u20132406 (2015)","DOI":"10.1109\/ICCV.2015.276"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Xia, F., Liu, T.Y., Wang, J., Li, H., Li, H.: Listwise approach to learning to rank: theory and algorithm. In: ICML, pp. 1192\u20131199 (2008)","DOI":"10.1145\/1390156.1390306"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Xie, L., Tian, Q., Hong, R., Yan, S.: Hierarchical part matching for fine-grained visual categorization. In: ICCV, pp. 1641\u20131648 (2013)","DOI":"10.1109\/ICCV.2013.206"},{"key":"26_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Zhang","year":"2014","unstructured":"Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_54"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xiong, H., Zhou, W., Lin, W., Tian, Q.: Picking deep filter responses for fine-grained image recognition. In: CVPR, June 2016","DOI":"10.1109\/CVPR.2016.128"},{"issue":"6","key":"26_CR48","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.: Diversified visual attention networks for fine-grained object classification. Trans. Multi. 19(6), 1245\u20131256 (2017)","journal-title":"Trans. Multi."},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: ICCV, October 2017","DOI":"10.1109\/ICCV.2017.557"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01264-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:53:25Z","timestamp":1775242405000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01264-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012632","9783030012649"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01264-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}