{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:10:21Z","timestamp":1771697421525,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642374302","type":"print"},{"value":"9783642374319","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-37431-9_44","type":"book-chapter","created":{"date-parts":[[2013,3,27]],"date-time":"2013-03-27T01:17:21Z","timestamp":1364347041000},"page":"572-585","source":"Crossref","is-referenced-by-count":41,"title":["A Comparative Study of Encoding, Pooling and Normalization Methods for Action Recognition"],"prefix":"10.1007","author":[{"given":"Xingxing","family":"Wang","sequence":"first","affiliation":[]},{"given":"LiMin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Liu, L., Wang, L., Liu, X.: In defense of soft-assignment coding. In: ICCV, pp. 2486\u20132493 (2011)","DOI":"10.1109\/ICCV.2011.6126534"},{"key":"44_CR2","unstructured":"Yang, J., Yu, K., Gong, Y., Huang, T.S.: Linear spatial pyramid matching using sparse coding for image classification. In: CVPR, pp. 1794\u20131801 (2009)"},{"key":"44_CR3","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, J., Yu, K., Lv, F., Huang, T.S., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR, pp. 3360\u20133367 (2010)","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"44_CR4","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":"44_CR5","doi-asserted-by":"crossref","unstructured":"Sch\u00fcldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local svm approach. In: ICPR, vol.\u00a03, pp. 32\u201336 (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: A large video database for human motion recognition. In: ICCV, pp. 2556\u20132563 (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"44_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"J. Aggarwal","year":"2011","unstructured":"Aggarwal, J., Ryoo, M.: Human activity analysis: A review. ACM Comput. Surv.\u00a043, 1\u201343 (2011)","journal-title":"ACM Comput. Surv."},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Turaga, P.K., Chellappa, R., Subrahmanian, V.S., Udrea, O.: Machine recognition of human activities: A survey. TCSVT, 1473 \u20131488 (2008)","DOI":"10.1109\/TCSVT.2008.2005594"},{"key":"44_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-642-15552-9_29","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J.C. Niebles","year":"2010","unstructured":"Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 392\u2013405. Springer, Heidelberg (2010)"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Tang, K., Fei-Fei, L., Koller, D.: Learning latent temporal structure for complex event detection. In: CVPR, pp. 1250\u20131257 (2012)","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR, pp. 2929\u20132936 (2009)","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Kovashka, A., Grauman, K.: Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In: CVPR, pp. 2046\u20132053 (2010)","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Brendel, W., Todorovic, S.: Learning spatiotemporal graphs of human activities. In: ICCV, pp. 778\u2013785 (2011)","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"44_CR14","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, pp. 1\u201322 (2004)"},{"key":"44_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-540-88690-7_52","volume-title":"Computer Vision \u2013 ECCV 2008","author":"J.C. Gemert van","year":"2008","unstructured":"van Gemert, J.C., Geusebroek, J.-M., Veenman, C.J., Smeulders, A.W.M.: Kernel Codebooks for Scene Categorization. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol.\u00a05304, pp. 696\u2013709. Springer, Heidelberg (2008)"},{"key":"44_CR16","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)"},{"key":"44_CR17","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s11263-006-9794-4","volume":"73","author":"J. Zhang","year":"2007","unstructured":"Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: A comprehensive study. IJCV\u00a073, 213\u2013238 (2007)","journal-title":"IJCV"},{"key":"44_CR18","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M. Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV\u00a088, 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"44_CR19","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I. Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. IJCV\u00a064, 107\u2013123 (2005)","journal-title":"IJCV"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: 2005 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 65\u201372 (2005)","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"44_CR22","unstructured":"Bishop, C.M.: Pattern Recognition and Machiner Learning. Springer (2006)"},{"key":"44_CR23","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/BF02289588","volume":"32","author":"S. Johnson","year":"1967","unstructured":"Johnson, S.: Hierarchical clustering schemes. Psychometrika\u00a032, 241\u2013254 (1967)","journal-title":"Psychometrika"},{"key":"44_CR24","unstructured":"Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: NIPS, vol.\u00a0(2), pp. 849\u2013856."},{"key":"44_CR25","unstructured":"Jaakkola, T., Haussler, D.: Exploiting generative models in discriminative classifiers. In: NIPS, pp. 487\u2013493 (1998)"},{"key":"44_CR26","unstructured":"Boureau, Y., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: ICML (2010)"},{"key":"44_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C.C. Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology\u00a02, 27:1\u201327:27 (2011)","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"44_CR28","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.: Action bank: A high-level representation of activity in video. In: CVPR, pp. 1234\u20131241 (2012)","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"44_CR29","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In: ICCV, pp. 1593\u20131600 (2009)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"44_CR30","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., Savarese, S.: Recognizing human actions by attributes. In: CVPR, pp. 3337\u20133344 (2011)","DOI":"10.1109\/CVPR.2011.5995353"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-37431-9_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T02:13:29Z","timestamp":1745979209000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-37431-9_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642374302","9783642374319"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-37431-9_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013]]}}}