{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:39:32Z","timestamp":1775281172974,"version":"3.50.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319105833","type":"print"},{"value":"9783319105840","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-10584-0_26","type":"book-chapter","created":{"date-parts":[[2014,8,14]],"date-time":"2014-08-14T11:40:08Z","timestamp":1408016408000},"page":"392-407","source":"Crossref","is-referenced-by-count":504,"title":["Multi-scale Orderless Pooling of Deep Convolutional Activation Features"],"prefix":"10.1007","author":[{"given":"Yunchao","family":"Gong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svetlana","family":"Lazebnik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"26_CR1","unstructured":"LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., Jackel, L.: Handwritten digit recognition with a back-propagation network. In: NIPS (1990)"},{"key":"26_CR2","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol.\u00a025, pp. 1106\u20131114 (2012)"},{"key":"26_CR3","unstructured":"Goodfellow, I., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. In: ICML (2013)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Le, Q., Ranzato, M., Monga, R., Devin, M., Chen, K., Corrado, G., Dean, J., Ng, A.: Building high-level features using large scale unsupervised learning. In: ICML (2012)","DOI":"10.1109\/ICASSP.2013.6639343"},{"key":"26_CR5","unstructured":"Wan, L., Zeiler, M., Zhang, S., Lecun, Y., Fergus, R.: Regularization of neural networks using DropConnect. In: ICML (2013)"},{"key":"26_CR6","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. Arxiv preprint arXiv:1207.0580 (2012)"},{"key":"26_CR7","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep fisher networks for large-scale image classification. In: Proceedings Advances in Neural Information Processing Systems (NIPS) (2013)"},{"key":"26_CR8","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: A deep convolutional activation feature for generic visual recognition. arXiv preprint arXiv:1310.1531 (2013)"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv preprint arXiv:1311.2524 (2013)","DOI":"10.1109\/CVPR.2014.81"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J., et al.: Learning and transferring mid-level image representations using convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.222"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: An astounding baseline for recognition. In: CVPR 2014 DeepVision Workshop (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"26_CR12","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)"},{"key":"26_CR13","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR14","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.R.: Fisher kernels on visual vocabularies for image categorization. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: CVPR, pp. 3304\u20133311 (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"26_CR17","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: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"26_CR18","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: ECCV Workshop on Statistical Learning in Computer Vision (2004)"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: ICCV, pp. 1458\u20131465 (2005)","DOI":"10.1109\/ICCV.2005.239"},{"issue":"2","key":"26_CR21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D.G. Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV\u00a060(2), 91\u2013110 (2004)","journal-title":"IJCV"},{"key":"26_CR22","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional neural networks. arXiv preprint arXiv:1311.2901 (2013)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: ICML, pp. 609\u2013616 (2009)","DOI":"10.1145\/1553374.1553453"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Jia, Y.: Caffe: An open source convolutional architecture for fast feature embedding (2013), \n                    \n                      http:\/\/caffe.berkeleyvision.org\/","DOI":"10.1145\/2647868.2654889"},{"key":"26_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F. Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the Fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.\u00a06314, pp. 143\u2013156. Springer, Heidelberg (2010)"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., Poirier, H.: Large-scale image retrieval with compressed Fisher vectors. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"26_CR27","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: SUN database: Large-scale scene recognition from abbey to zoo. In: CVPR, 3485\u20133492 (2010)"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Pandey, M., Lazebnik, S.: Scene recognition and weakly supervised object localization with deformable part-based models. In: ICCV, pp. 1307\u20131314 (2011)","DOI":"10.1109\/ICCV.2011.6126383"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: CVPR (2009)","DOI":"10.1109\/CVPRW.2009.5206537"},{"key":"26_CR30","unstructured":"Deng, J., Berg, A., Satheesh, S., Su, H., Khosla, A., Fei-Fei, L.: Large scale visual recognition challenge (2012), \n                    \n                      http:\/\/www.image-net.org\/challenges\/LSVRC\/2012\/"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Huang, Z., Berg, A., Fei-Fei, L.: Detecting avocados to zucchinis: what have we done, and where are we going? In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.258"},{"key":"26_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1007\/978-3-540-88682-2_24","volume-title":"Computer Vision \u2013 ECCV 2008","author":"H. Jegou","year":"2008","unstructured":"Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol.\u00a05302, pp. 304\u2013317. Springer, Heidelberg (2008)"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C., et al.: Good practice in large-scale learning for image classification. PAMI (2013)","DOI":"10.1109\/CVPR.2012.6248090"},{"issue":"3","key":"26_CR34","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J. Sanchez","year":"2013","unstructured":"Sanchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image Classification with the Fisher Vector: Theory and Practice. IJCV\u00a0105(3), 222\u2013245 (2013)","journal-title":"IJCV"},{"key":"26_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-642-33709-3_6","volume-title":"Computer Vision \u2013 ECCV 2012","author":"S. Singh","year":"2012","unstructured":"Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol.\u00a07573, pp. 73\u201386. Springer, Heidelberg (2012)"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Juneja, M., Vedaldi, A., Jawahar, C.V., Zisserman, A.: Blocks that shout: Distinctive parts for scene classification. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.124"},{"key":"26_CR37","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Mid-level visual element discovery as discriminative mode seeking. In: NIPS (2013)"},{"key":"26_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1007\/978-3-642-33709-3_55","volume-title":"Computer Vision \u2013 ECCV 2012","author":"H. J\u00e9gou","year":"2012","unstructured":"J\u00e9gou, H., Chum, O.: Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol.\u00a07573, pp. 774\u2013787. Springer, Heidelberg (2012)"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Gordo, A., Rodr\u0131guez-Serrano, J.A., Perronnin, F., Valveny, E.: Leveraging category-level labels for instance-level image retrieval. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248035"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Tolias, G., Avrithis, Y., J\u00e9gou, H.: To aggregate or not to aggregate: selective match kernels for image search. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.177"},{"key":"26_CR41","unstructured":"Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., Keutzer, K.: DenseNet: Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2014"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10584-0_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T09:48:42Z","timestamp":1575280122000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10584-0_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105833","9783319105840"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10584-0_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}