{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T06:45:24Z","timestamp":1794465924028,"version":"4.9.1"},"publisher-location":"London","reference-count":62,"publisher":"Springer London","isbn-type":[{"value":"9781447155195","type":"print"},{"value":"9781447155201","type":"electronic"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-1-4471-5520-1_3","type":"book-chapter","created":{"date-parts":[[2013,11,27]],"date-time":"2013-11-27T19:21:37Z","timestamp":1385580097000},"page":"65-93","source":"Crossref","is-referenced-by-count":1,"title":["Recognizing Human Actions by Using Effective Codebooks and Tracking"],"prefix":"10.1007","author":[{"given":"Lamberto","family":"Ballan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Seidenari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Bertini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"Del Bimbo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"issue":"2","key":"3_CR1","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1109\/78.978374","volume":"50","author":"M Arulampalam","year":"2002","unstructured":"Arulampalam M, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for online nonlinear\/non-Gaussian Bayesian tracking. IEEE Trans Signal Process 50(2):174\u2013188","journal-title":"IEEE Trans Signal Process"},{"key":"3_CR2","volume-title":"Proc of AVSS","author":"AD Bagdanov","year":"2007","unstructured":"Bagdanov AD, Dini F, Del Bimbo A, Nunziati W (2007) Improving the robustness of particle filter-based visual trackers using online parameter adaptation. In: Proc of AVSS"},{"issue":"1","key":"3_CR3","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/s11042-010-0643-7","volume":"51","author":"L Ballan","year":"2011","unstructured":"Ballan L, Bertini M, Del Bimbo A, Seidenari L, Serra G (2011) Event detection and recognition for semantic annotation of video. Multimed Tools Appl 51(1):279\u2013302","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"3_CR4","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1109\/TMM.2012.2191268","volume":"14","author":"L Ballan","year":"2012","unstructured":"Ballan L, Bertini M, Del Bimbo A, Seidenari L, Serra G (2012) Effective codebooks for human action representation and classification in unconstrained videos. IEEE Trans Multimed 14(4):1234\u20131245","journal-title":"IEEE Trans Multimed"},{"key":"3_CR5","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin K, Stiefelhagen R (2008) Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J Image Video Process 2008:246309","journal-title":"EURASIP J Image Video Process"},{"issue":"3","key":"3_CR6","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"AF Bobick","year":"2001","unstructured":"Bobick AF, Davis JW (2001) The recognition of human movement using temporal templates. IEEE Trans Pattern Anal Mach Intell 23(3):257\u2013267","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3_CR7","volume-title":"Proc of CVPR","author":"M Bregonzio","year":"2009","unstructured":"Bregonzio M, Gong S, Xiang T (2009) Recognising action as clouds of space-time interest points. In: Proc of CVPR"},{"key":"3_CR8","volume-title":"Proc of CVPR","author":"L Cao","year":"2010","unstructured":"Cao L, Zicheng L, Huang T (2010) Cross-dataset action detection. In: Proc of CVPR"},{"key":"3_CR9","volume-title":"Proc of AISTATS","author":"MA Carreira Perpinan","year":"2005","unstructured":"Carreira Perpinan MA, Hinton GE (2005) On contrastive divergence learning. In: Proc of AISTATS"},{"key":"3_CR10","unstructured":"Chen MY, Hauptmann AG (2009) MoSIFT: recognizing human actions in surveillance videos. Technical report, CMU"},{"issue":"5","key":"3_CR11","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D Comaniciu","year":"2002","unstructured":"Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603\u2013619","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3_CR12","volume-title":"Proc of CVPR","author":"N Dalal","year":"2005","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proc of CVPR"},{"key":"3_CR13","volume-title":"Proc of VSPETS","author":"P Doll\u00e1r","year":"2005","unstructured":"Doll\u00e1r P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features. In: Proc of VSPETS"},{"key":"3_CR14","volume-title":"Proc of ICCV","author":"AA Efros","year":"2003","unstructured":"Efros AA, Berg AC, Mori G, Malik J (2003) Recognizing action at a distance. In: Proc of ICCV"},{"key":"3_CR15","volume-title":"Proc of CVPR","author":"R Fergus","year":"2003","unstructured":"Fergus R, Perona P, Zisserman A (2003) Object class recognition by unsupervised scale-invariant learning. In: Proc of CVPR"},{"key":"3_CR16","volume-title":"Proc of HBU workshop","author":"Z Gao","year":"2010","unstructured":"Gao Z, Chen MY, Hauptmann AG, Cai A (2010) Comparing evaluation protocols on the KTH dataset. In: Proc of HBU workshop"},{"issue":"12","key":"3_CR17","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick L, Blank M, Schechtman E, Irani M, Basri R (2007) Actions as space-time shapes. IEEE Trans Pattern Anal Mach Intell 29(12):2247\u20132253","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"3_CR18","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1109\/JPROC.2008.916355","volume":"96","author":"AG Hauptmann","year":"2008","unstructured":"Hauptmann AG, Christel MG, Yan R (2008) Video retrieval based on semantic concepts. Proc IEEE 96(4):602\u2013622","journal-title":"Proc IEEE"},{"issue":"5786","key":"3_CR19","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"EG Hinton","year":"2006","unstructured":"Hinton EG, Salakhutdinov R (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"issue":"7","key":"3_CR20","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"EG Hinton","year":"2006","unstructured":"Hinton EG, Osindero S, Teh Y (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527\u20131554","journal-title":"Neural Comput"},{"issue":"1","key":"3_CR21","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/TMM.2009.2036235","volume":"12","author":"YG Jiang","year":"2010","unstructured":"Jiang YG, Yang J, Ngo CW, Hauptmann AG (2010) Representations of keypoint-based semantic concept detection: a comprehensive study. IEEE Trans Multimed 12(1):42\u201353","journal-title":"IEEE Trans Multimed"},{"key":"3_CR22","volume-title":"Proc of ICCV","author":"F Jurie","year":"2005","unstructured":"Jurie F, Triggs B (2005) Creating efficient codebooks for visual recognition. In: Proc of ICCV"},{"key":"3_CR23","volume-title":"Proc of BMVC","author":"A Kl\u00e4ser","year":"2008","unstructured":"Kl\u00e4ser A, Marsza\u0142ek M, Schmid C (2008) A spatio-temporal descriptor based on 3D-gradients. In: Proc of BMVC"},{"issue":"8","key":"3_CR24","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1016\/j.patrec.2011.03.006","volume":"32","author":"Y Kong","year":"2011","unstructured":"Kong Y, Zhang X, Hu W, Jia Y (2011) Adaptive learning codebook for action recognition. Pattern Recognit Lett 32(8):1178\u20131186","journal-title":"Pattern Recognit Lett"},{"key":"3_CR25","volume-title":"Proc of CVPR","author":"A Kovashka","year":"2010","unstructured":"Kovashka A, Grauman K (2010) Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In: Proc of CVPR"},{"issue":"2\u20133","key":"3_CR26","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev I (2005) On space-time interest points. Int J Comput Vis 64(2\u20133):107\u2013123","journal-title":"Int J Comput Vis"},{"key":"3_CR27","volume-title":"Proc of CVPR","author":"I Laptev","year":"2008","unstructured":"Laptev I, Marsza\u0142ek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: Proc of CVPR"},{"key":"3_CR28","volume-title":"Proc of CVPR","author":"S Lazebnik","year":"2006","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proc of CVPR"},{"key":"3_CR29","volume-title":"Proc of ICCV","author":"Z Lin","year":"2009","unstructured":"Lin Z, Jiang Z, Davis LS (2009) Recognizing actions by shape-motion prototype trees. In: Proc of ICCV"},{"key":"3_CR30","volume-title":"Proc of CVPR","author":"J Liu","year":"2008","unstructured":"Liu J, Shah M (2008) Learning human actions via information maximization. In: Proc of CVPR"},{"key":"3_CR31","volume-title":"Proc of CVPR","author":"J Liu","year":"2008","unstructured":"Liu J, Ali S, Shah M (2008) Recognizing human actions using multiple features. In: Proc of CVPR"},{"key":"3_CR32","volume-title":"Proc of CVPR","author":"J Liu","year":"2009","unstructured":"Liu J, Luo J, Shah M (2009) Recognizing realistic actions from videos \u201cin the wild\u201d. In: Proc of CVPR"},{"key":"3_CR33","volume-title":"Proc of DARPA IU workshop","author":"BD Lucas","year":"1981","unstructured":"Lucas BD, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: Proc of DARPA IU workshop"},{"key":"3_CR34","volume-title":"Proc of CVPR","author":"M Marsza\u0142ek","year":"2009","unstructured":"Marsza\u0142ek M, Laptev I, Schmid C (2009) Actions in context. In: Proc of CVPR"},{"key":"3_CR35","volume-title":"Proc of CVPR","author":"K Mikolajczyk","year":"2008","unstructured":"Mikolajczyk K, Uemura H (2008) Action recognition with motion-appearance vocabulary forest. In: Proc of CVPR"},{"key":"3_CR36","volume-title":"Proc of ICCV","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk K, Leibe B, Schiele B (2005) Local features for object class recognition. In: Proc of ICCV"},{"issue":"1\/2","key":"3_CR37","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s11263-005-3848-x","volume":"65","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Van\u00a0Gool L (2005) A comparison of affine region detectors. Int J Comput Vis 65(1\/2):43\u201372","journal-title":"Int J Comput Vis"},{"issue":"2\u20133","key":"3_CR38","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","volume":"104","author":"T Moeslund","year":"2006","unstructured":"Moeslund T, Hilton A, Kr\u00fcger V (2006) A survey of advances in vision-based human motion capture and analysis. Comput Vis Image Underst 104(2\u20133):90\u2013126","journal-title":"Comput Vis Image Underst"},{"issue":"3","key":"3_CR39","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles JC, Wang H, Fei-Fei L (2008) Unsupervised learning of human action categories using spatial-temporal words. Int J Comput Vis 79(3):299\u2013318","journal-title":"Int J Comput Vis"},{"issue":"1\u20132","key":"3_CR40","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.cviu.2006.10.016","volume":"108","author":"R Poppe","year":"2007","unstructured":"Poppe R (2007) Vision-based human motion analysis: an overview. Comput Vis Image Underst 108(1\u20132):4\u201318","journal-title":"Comput Vis Image Underst"},{"issue":"6","key":"3_CR41","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe R (2010) A survey on vision-based human action recognition. Image Vis Comput 28(6):976\u2013990","journal-title":"Image Vis Comput"},{"key":"3_CR42","volume-title":"Proc of CVPR","author":"K Rapantzikos","year":"2009","unstructured":"Rapantzikos K, Avrithis Y, Kollia S (2009) Dense saliency-based spatiotemporal feature points for action recognition. In: Proc of CVPR"},{"key":"3_CR43","volume-title":"Proc of ICPR","author":"C Sch\u00fcldt","year":"2004","unstructured":"Sch\u00fcldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local SVM approach. In: Proc of ICPR"},{"key":"3_CR44","volume-title":"Proc of ACM multimedia","author":"P Scovanner","year":"2007","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3-dimensional SIFT descriptor and its application to action recognition. In: Proc of ACM multimedia"},{"key":"3_CR45","volume-title":"Proc of CIVR","author":"L Shao","year":"2010","unstructured":"Shao L, Mattivi R (2010) Feature detector and descriptor evaluation in human action recognition. In: Proc of CIVR"},{"issue":"6","key":"3_CR46","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1016\/j.neucom.2010.11.013","volume":"74","author":"L Shao","year":"2011","unstructured":"Shao L, Gao R, Liu Y, Zhang H (2011) Transform based spatio-temporal descriptors for human action recognition. Neurocomputing 74(6):962\u2013973","journal-title":"Neurocomputing"},{"key":"3_CR47","volume-title":"Proc of ICCV","author":"J Sivic","year":"2003","unstructured":"Sivic J, Zisserman A (2003) Video Google: a text retrieval approach to object matching in videos. In: Proc of ICCV"},{"key":"3_CR48","volume-title":"Proc of ACM multimedia","author":"CGM Snoek","year":"2006","unstructured":"Snoek CGM, Worring M, van Gemert JC, Geusebroek JM, Smeulders AWM (2006) The challenge problem for automated detection of 101 semantic concepts in multimedia. In: Proc of ACM multimedia"},{"key":"3_CR49","volume-title":"Proc of CVPR4HB workshop","author":"X Sun","year":"2009","unstructured":"Sun X, Chen M, Hauptmann AG (2009) Action recognition via local descriptors and holistic features. In: Proc of CVPR4HB workshop"},{"issue":"11","key":"3_CR50","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1109\/TCSVT.2008.2005594","volume":"18","author":"P Turaga","year":"2008","unstructured":"Turaga P, Chellappa R, Subrahmanian V, Udrea O (2008) Machine recognition of human activities: a survey. IEEE Trans Circuits Syst Video Technol 18(11):1473\u20131488","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"3_CR51","unstructured":"van der Maaten L, Postma E, van den Herik H (2009) Dimensionality reduction: a comparative review. Technical report TiCC-TR 2009-005, Tilburg University"},{"issue":"7","key":"3_CR52","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1109\/TPAMI.2009.132","volume":"32","author":"JC van Gemert","year":"2010","unstructured":"van Gemert JC, Veenman CJ, Smeulders AWM, Geusebroek JM (2010) Visual word ambiguity. IEEE Trans Pattern Anal Mach Intell 32(7):1271\u20131283","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"3_CR53","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s11042-009-0402-9","volume":"50","author":"R Vezzani","year":"2010","unstructured":"Vezzani R, Cucchiara R (2010) Video surveillance online repository (ViSOR): an integrated framework. Multimed Tools Appl 50(2):359\u2013380","journal-title":"Multimed Tools Appl"},{"key":"3_CR54","volume-title":"Proc of CVPR","author":"Y Wang","year":"2009","unstructured":"Wang Y, Mori G (2009) Max-margin hidden conditional random fields for human action recognition. In: Proc of CVPR"},{"key":"3_CR55","volume-title":"Proc of BMVC","author":"H Wang","year":"2009","unstructured":"Wang H, Ullah MM, Kl\u00e4ser A, Laptev I, Schmid C (2009) Evaluation of local spatio-temporal features for action recognition. In: Proc of BMVC"},{"key":"3_CR56","volume-title":"Proc of ECCV","author":"G Willems","year":"2008","unstructured":"Willems G, Tuytelaars T, Van Gool L (2008) An efficient dense and scale-invariant spatio-temporal interest point detector. In: Proc of ECCV"},{"key":"3_CR57","volume-title":"Proc of ICCV","author":"SF Wong","year":"2007","unstructured":"Wong SF, Cipolla R (2007) Extracting spatiotemporal interest points using global information. In: Proc of ICCV"},{"issue":"2","key":"3_CR58","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s11263-006-0027-7","volume":"75","author":"B Wu","year":"2007","unstructured":"Wu B, Nevatia R (2007) Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. Int J Comput Vis 75(2):247\u2013266","journal-title":"Int J Comput Vis"},{"key":"3_CR59","volume-title":"Proc of CVPR","author":"A Yao","year":"2010","unstructured":"Yao A, Gall J, Van Gool L (2010) A hough transform-based voting framework for action recognition. In: Proc of CVPR"},{"key":"3_CR60","volume-title":"Proc of CVPR","author":"A Yilmaz","year":"2005","unstructured":"Yilmaz A, Shah M (2005) Actions sketch: a novel action representation. In: Proc of CVPR"},{"issue":"3","key":"3_CR61","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1109\/TMM.2011.2128301","volume":"13","author":"G Yu","year":"2011","unstructured":"Yu G, Goussies N, Yuan J, Liu Z (2011) Fast action detection via discriminative random forest voting and top-k subvolume search. IEEE Trans Multimed 13(3):507\u2013517","journal-title":"IEEE Trans Multimed"},{"issue":"2","key":"3_CR62","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s11263-006-9794-4","volume":"73","author":"J Zhang","year":"2007","unstructured":"Zhang J, Marsza\u0142ek M, Lazebnik S, Schmid C (2007) Local features and kernels for classification of texture and object categories: a comprehensive study. Int J Comput Vis 73(2):213\u2013238","journal-title":"Int J Comput Vis"}],"container-title":["Advances in Computer Vision and Pattern Recognition","Advanced Topics in Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4471-5520-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T11:49:19Z","timestamp":1676634559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4471-5520-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9781447155195","9781447155201"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-1-4471-5520-1_3","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-1-4471-5520-1","asserted-by":"object"}]},"ISSN":["2191-6586","2191-6594"],"issn-type":[{"value":"2191-6586","type":"print"},{"value":"2191-6594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013]]}}}