{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:55:26Z","timestamp":1775109326215,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030305079","type":"print"},{"value":"9783030305086","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-30508-6_5","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T23:02:47Z","timestamp":1567983767000},"page":"55-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Aggregating Rich Deep Semantic Features for Fine-Grained Place Classification"],"prefix":"10.1007","author":[{"given":"Tingyu","family":"Wei","sequence":"first","affiliation":[]},{"given":"Wenxin","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xingjiao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yingbin","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2911\u20132918 (2012). https:\/\/doi.org\/10.1109\/cvpr.2012.6248018","DOI":"10.1109\/cvpr.2012.6248018"},{"key":"5_CR2","doi-asserted-by":"publisher","first-page":"66322","DOI":"10.1109\/access.2018.2878899","volume":"6","author":"X Bai","year":"2018","unstructured":"Bai, X., Yang, M., Lyu, P., Xu, Y., Luo, J.: Integrating scene text and visual appearance for fine-grained image classification. IEEE Access 6, 66322\u201366335 (2018). https:\/\/doi.org\/10.1109\/access.2018.2878899","journal-title":"IEEE Access"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Branson, S., Van Horn, G., Belongie, S., Perona, P.: Bird species categorization using pose normalized deep convolutional nets. arXiv preprint arXiv:1406.2952 (2014)","DOI":"10.5244\/C.28.87"},{"key":"5_CR4","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27 (2011). https:\/\/doi.org\/10.1145\/1961189.1961199","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"5_CR5","doi-asserted-by":"publisher","unstructured":"Gavves, E., Fernando, B., Snoek, C.G., Smeulders, A.W., Tuytelaars, T.: Fine-grained categorization by alignments. In: International Conference on Computer Vision (ICCV), pp. 1713\u20131720 (2013). https:\/\/doi.org\/10.1109\/iccv.2013.215","DOI":"10.1109\/iccv.2013.215"},{"key":"5_CR6","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s11263-014-0741-5","volume":"111","author":"E Gavves","year":"2015","unstructured":"Gavves, E., Fernando, B., Snoek, C.G., Smeulders, A.W., Tuytelaars, T.: Local alignments for fine-grained categorization. Int. J. Comput. Vis. 111, 191\u2013212 (2015). https:\/\/doi.org\/10.1007\/s11263-014-0741-5","journal-title":"Int. J. Comput. Vis."},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"5_CR8","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv Preprint arXiv:1406.2227 (2014)"},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"Karaoglu, S., van Gemert, J.C., Gevers, T.: Con-text: text detection using background connectivity for fine-grained object classification. In: ACM International Conference on Multimedia (MM), pp. 757\u2013760 (2013). https:\/\/doi.org\/10.1145\/2502081.2502197","DOI":"10.1145\/2502081.2502197"},{"key":"5_CR10","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1109\/tip.2017.2707805","volume":"26","author":"S Karaoglu","year":"2017","unstructured":"Karaoglu, S., Tao, R., van Gemert, J.C., Gevers, T.: Con-text: text detection for fine-grained object classification. IEEE Trans. Image Process. 26, 3965\u20133980 (2017). https:\/\/doi.org\/10.1109\/tip.2017.2707805","journal-title":"IEEE Trans. Image Process."},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1109\/tmm.2016.2638622","volume":"19","author":"S Karaoglu","year":"2017","unstructured":"Karaoglu, S., Tao, R., Gevers, T., Smeulders, A.W.: Words matter: scene text for image classification and retrieval. IEEE Trans. Multimedia 19, 1063\u20131076 (2017). https:\/\/doi.org\/10.1109\/tmm.2016.2638622","journal-title":"IEEE Trans. Multimedia"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160 (2015). https:\/\/doi.org\/10.1109\/icdar.2015.7333942","DOI":"10.1109\/icdar.2015.7333942"},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2169\u20132178 (2006). https:\/\/doi.org\/10.1109\/cvpr.2006.68","DOI":"10.1109\/cvpr.2006.68"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: TextBoxes: a fast text detector with a single deep neural network. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 4161\u20134167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"5_CR15","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"},{"key":"5_CR16","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/tmm.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimedia 20, 3111\u20133122 (2018). https:\/\/doi.org\/10.1109\/tmm.2018.2818020","journal-title":"IEEE Trans. Multimedia"},{"key":"5_CR17","doi-asserted-by":"publisher","unstructured":"Movshovitz-Attias, Y., Yu, Q., Stumpe, M.C., Shet, V., Arnoud, S., Yatziv, L.: Ontological supervision for fine grained classification of street view storefronts. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1693\u20131702 (2015). https:\/\/doi.org\/10.1109\/cvpr.2015.7298778","DOI":"10.1109\/cvpr.2015.7298778"},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), pp. 722\u2013729 (2008). https:\/\/doi.org\/10.1109\/icvgip.2008.47","DOI":"10.1109\/icvgip.2008.47"},{"key":"5_CR19","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vision 42, 145\u2013175 (2001)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR20","doi-asserted-by":"publisher","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 413\u2013420 (2009). https:\/\/doi.org\/10.1109\/cvprw.2009.5206537","DOI":"10.1109\/cvprw.2009.5206537"},{"key":"5_CR21","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. Int. J. Comput. Vision 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv Preprint arXiv:1409.1556 (2014)"},{"key":"5_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-319-46484-8_4","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Tian","year":"2016","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4"},{"key":"5_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-642-15549-9_56","volume-title":"Computer Vision \u2013 ECCV 2010","author":"L Torresani","year":"2010","unstructured":"Torresani, L., Szummer, M., Fitzgibbon, A.: Efficient object category recognition using classemes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 776\u2013789. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_56"},{"issue":"2","key":"5_CR25","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s11263-006-8614-1","volume":"72","author":"J Vogel","year":"2007","unstructured":"Vogel, J., Schiele, B.: Semantic modeling of natural scenes for content-based image retrieval. Int. J. Comput. Vision 72(2), 133\u2013157 (2007). https:\/\/doi.org\/10.1007\/s11263-006-8614-1","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3485\u20133492 (2010). https:\/\/doi.org\/10.1109\/cvpr.2010.5539970","DOI":"10.1109\/cvpr.2010.5539970"},{"key":"5_CR27","doi-asserted-by":"publisher","unstructured":"Xiao, T., Xu, Y., Yang, K., Zhang, J., Peng, Y., Zhang, Z.: The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 842\u2013850 (2015). https:\/\/doi.org\/10.1109\/cvpr.2015.7298685","DOI":"10.1109\/cvpr.2015.7298685"},{"key":"5_CR28","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":"5_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-642-33715-4_13","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y Zheng","year":"2012","unstructured":"Zheng, Y., Jiang, Y.-G., Xue, X.: Learning hybrid part filters for scene recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 172\u2013185. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_13"},{"key":"5_CR30","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/tpami.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1452\u20131464 (2017). https:\/\/doi.org\/10.1109\/tpami.2017.2723009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR31","doi-asserted-by":"publisher","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2642\u20132651 (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.283","DOI":"10.1109\/cvpr.2017.283"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Image Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30508-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T21:34:13Z","timestamp":1664314453000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30508-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030305079","9783030305086"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30508-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}