{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:44:58Z","timestamp":1742913898107,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030054984"},{"type":"electronic","value":"9783030054991"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05499-1_3","type":"book-chapter","created":{"date-parts":[[2019,1,4]],"date-time":"2019-01-04T17:36:40Z","timestamp":1546623400000},"page":"44-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CNN-Based Deep Spatial Pyramid Match Kernel for Classification of Varying Size Images"],"prefix":"10.1007","author":[{"given":"Shikha","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manjush","family":"Mangal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshay","family":"Mathew","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dileep Aroor","family":"Dinesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnav","family":"Bhavsar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Veena","family":"Thenkanidiyoor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,5]]},"reference":[{"key":"3_CR1","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: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 955\u2013962. IEEE (2013)","DOI":"10.1109\/CVPR.2013.128"},{"key":"3_CR2","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"},{"issue":"3","key":"3_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"Chih-Chung Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1\u201327:27 (2011)","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv:1405.3531 (2014)","DOI":"10.5244\/C.28.6"},{"key":"3_CR5","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, vol. 1, pp. 1\u20132. Prague (2004)"},{"key":"3_CR6","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 886\u2013893 (2005)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"8","key":"3_CR8","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1109\/TNNLS.2013.2293512","volume":"25","author":"AD Dileep","year":"2014","unstructured":"Dileep, A.D., Chandra Sekhar, C.: GMM-based intermediate matching kernel for classification of varying length patterns of long duration speech using support vector machines. IEEE Trans. Neural Netw. Learn. Syst. 25(8), 1421\u20131432 (2014)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3_CR9","unstructured":"Donahue, J., et al.: Decaf: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning, pp. 647\u2013655 (2014)"},{"issue":"9","key":"3_CR10","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR11","unstructured":"Gao, B.B., Wei, X.S., Wu, J., Lin, W.: Deep spatial pyramid: the devil is once again in the details. CoRR abs\/1504.05277 (2015)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: 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 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"3_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-319-10584-0_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Gong","year":"2014","unstructured":"Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 392\u2013407. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_26"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"G\u00f6ring, C., Rodner, E., Freytag, A., Denzler, J.: Nonparametric part transfer for fine-grained recognition. In: CVPR, vol. 1, p. 7 (2014)","DOI":"10.1109\/CVPR.2014.319"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, S., Dileep, A.D., Thenkanidiyoor, V.: Segment-level pyramid match kernels for the classification of varying length patterns of speech using svms. In: 2016 24th European Signal Processing Conference (EUSIPCO), pp. 2030\u20132034. IEEE (2016)","DOI":"10.1109\/EUSIPCO.2016.7760605"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, S., Pradhan, D., Dileep, A.D., Thenkanidiyoor, V.: Deep spatial pyramid match kernel for scene classification. In: ICPRAM, pp. 141\u2013148 (2018)","DOI":"10.5220\/0006596101410148"},{"key":"3_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-319-46681-1_39","volume-title":"Neural Information Processing","author":"S Gupta","year":"2016","unstructured":"Gupta, S., Thenkanidiyoor, V., Aroor Dinesh, D.: Segment-level probabilistic sequence kernel based support vector machines for classification of varying length patterns of speech. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9950, pp. 321\u2013328. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46681-1_39"},{"issue":"9","key":"3_CR18","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. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"3_CR19","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1080\/13506280444000544","volume":"12","author":"J Henderson","year":"2005","unstructured":"Henderson, J.: Introduction to real-world scene perception. Vis. Cogn. 12(6), 849\u2013851 (2005)","journal-title":"Vis. Cogn."},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3304\u20133311. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Juneja, M., Vedaldi, A., Jawahar, C., Zisserman, A.: Blocks that shout: distinctive parts for scene classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 923\u2013930 (2013)","DOI":"10.1109\/CVPR.2013.124"},{"key":"3_CR22","unstructured":"Kang, K., Wang, X.: Fully convolutional neural networks for crowd segmentation. arXiv preprint arXiv:1411.4464 (2014)"},{"key":"3_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"3_CR24","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 2169\u20132178 (2006)"},{"issue":"2","key":"3_CR25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR26","unstructured":"Mandar, D., Chen, S., Gao, D., Rasiwasia, N., Nuno, V.: Scene classification with semantic fisher vectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2974\u20132983 (2015)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Sixth Indian Conference on Computer Vision, Graphics & Image Processing, ICVGIP 2008, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"issue":"3","key":"3_CR28","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. Vis. 42(3), 145\u2013175 (2001)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 413\u2013420. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Simon, M., Rodner, E.: Neural activation constellations: Unsupervised part model discovery with convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.136"},{"key":"3_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"2","key":"3_CR33","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., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-540-27814-6_27","volume-title":"Image and Video Retrieval","author":"J Vogel","year":"2004","unstructured":"Vogel, J., Schiele, B.: Natural scene retrieval based on a semantic modeling step. In: Enser, P., Kompatsiaris, Y., O\u2019Connor, N.E., Smeaton, A.F., Smeulders, A.W.M. (eds.) CIVR 2004. LNCS, vol. 3115, pp. 207\u2013215. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-27814-6_27"},{"key":"3_CR35","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3360\u20133367 (2010)","DOI":"10.1109\/CVPR.2010.5540018"},{"issue":"2","key":"3_CR37","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1109\/TIP.2012.2218826","volume":"22","author":"Z Wang","year":"2013","unstructured":"Wang, Z., Feng, J., Yan, S., Xi, H.: Linear distance coding for image classification. IEEE Trans. Image Process. 22(2), 537\u2013548 (2013)","journal-title":"IEEE Trans. Image Process."},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"3_CR39","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: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 842\u2013850. IEEE (2015)"},{"key":"3_CR40","unstructured":"Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1794\u20131801 (2009)"},{"key":"3_CR41","unstructured":"Yoo, D., Park, S., Lee, J.Y., Kweon, I.S.: Fisher kernel for deep neural activations. arXiv preprint arXiv:1412.1628 (2014)"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Yoo, D., Park, S., Lee, J.Y., So Kweon, I.: Multi-scale pyramid pooling for deep convolutional representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 71\u201380 (2015)","DOI":"10.1109\/CVPRW.2015.7301274"},{"key":"3_CR43","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":"3_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, N., Farrell, R., Iandola, F., Darrell, T.: Deformable part descriptors for fine-grained recognition and attribute prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 729\u2013736 (2013)","DOI":"10.1109\/ICCV.2013.96"},{"key":"3_CR45","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR46","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: Advances in Neural Information Processing Systems, pp. 487\u2013495 (2014)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition Applications and Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05499-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T01:03:57Z","timestamp":1672794237000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-05499-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030054984","9783030054991"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05499-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"5 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition Applications and Methods","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Funchal","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 January 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 January 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpram2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpram.org\/?y=2018","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"102","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}