{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:27:56Z","timestamp":1778081276805,"version":"3.51.4"},"reference-count":89,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,3,15]],"date-time":"2016-03-15T00:00:00Z","timestamp":1458000000000},"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":["Artif Intell Rev"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1007\/s10462-016-9473-y","type":"journal-article","created":{"date-parts":[[2016,3,18]],"date-time":"2016-03-18T20:43:06Z","timestamp":1458333786000},"page":"485-514","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["A review on human action analysis in videos for retrieval applications"],"prefix":"10.1007","volume":"46","author":[{"given":"Mohsen","family":"Ramezani","sequence":"first","affiliation":[]},{"given":"Farzin","family":"Yaghmaee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,3,15]]},"reference":[{"key":"9473_CR1","unstructured":"Akp\u0131nar S, Alpaslan FN (2014) Video action recognition using an optical flow based representation"},{"key":"9473_CR2","doi-asserted-by":"crossref","unstructured":"Arman F, Depommier R, Hsu A, Chiu MY (1994) Content-based browsing of video sequences. In: Proceedings of the second ACM international conference on Multimedia. ACM, pp 97\u2013103","DOI":"10.1145\/192593.192630"},{"issue":"15","key":"9473_CR3","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1016\/j.patrec.2012.12.020","volume":"34","author":"M Barnachon","year":"2013","unstructured":"Barnachon M, Bouakaz S, Boufama B, Guillou E (2013) A real-time system for motion retrieval and interpretation. Pattern Recognit Lett 34(15):1789\u20131798","journal-title":"Pattern Recognit Lett"},{"issue":"8","key":"9473_CR4","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1109\/TPAMI.2002.1023805","volume":"24","author":"J Ben-Arie","year":"2002","unstructured":"Ben-Arie J, Wang Z, Pandit P, Rajaram S (2002) Human activity recognition using multidimensional indexing. IEEE Trans Pattern Anal Mach Intell 24(8):1091\u20131104","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9473_CR5","doi-asserted-by":"crossref","unstructured":"Bregonzio M, Gong S, Xiang T (2009) Recognising action as clouds of space-time interest points. In: Computer vision and pattern recognition, 2009. CVPR 2009. IEEE conference on. IEEE, pp 1948\u20131955","DOI":"10.1109\/CVPR.2009.5206779"},{"key":"9473_CR6","doi-asserted-by":"crossref","unstructured":"Bulbul MF, Jiang Y, Ma J (2015) Human action recognition based on DMMs, HOGs and contourlet transform","DOI":"10.1109\/BigMM.2015.82"},{"key":"9473_CR7","doi-asserted-by":"crossref","unstructured":"Caicedo JC, Gonz\u00e1lez FA (2012) Multimodal fusion for image retrieval using matrix factorization. In: Proceedings of the 2nd ACM international conference on multimedia retrieval. ACM, p 56","DOI":"10.1145\/2324796.2324860"},{"key":"9473_CR8","doi-asserted-by":"crossref","unstructured":"Chen CY, Grauman K (2012) Efficient activity detection with max-subgraph search. In: Computer vision and pattern recognition (CVPR), 2012 IEEE conference on. IEEE, pp 1274\u20131281","DOI":"10.1109\/CVPR.2012.6247811"},{"key":"9473_CR9","doi-asserted-by":"crossref","unstructured":"Choi J, Jeon WJ, Lee SC (2008) Spatio-temporal pyramid matching for sports videos. In: Proceedings of the 1st ACM international conference on multimedia information retrieval. ACM, pp 291\u2013297","DOI":"10.1145\/1460096.1460144"},{"key":"9473_CR10","doi-asserted-by":"crossref","unstructured":"Ciptadi A, Goodwin MS, Rehg JM (2014) Movement pattern histogram for action recognition and retrieval. In: Computer vision\u2014ECCV 2014. Springer International Publishing, pp 695\u2013710","DOI":"10.1007\/978-3-319-10605-2_45"},{"key":"9473_CR11","doi-asserted-by":"crossref","unstructured":"Cohn DA, Ghahramani Z, Jordan MI (1996) Active learning with statistical models. J Artif Intell Res 4(17):129\u2013145","DOI":"10.1613\/jair.295"},{"key":"9473_CR12","doi-asserted-by":"crossref","unstructured":"Davis JW, Bobick AE (1997) The representation and recognition of human movement using temporal templates. In: Computer vision and pattern recognition, 1997. Proceedings., 1997 IEEE computer society conference on. IEEE, pp 928\u2013934","DOI":"10.1109\/CVPR.1997.609439"},{"key":"9473_CR13","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features. In: Visual surveillance and performance evaluation of tracking and surveillance, 2005. 2nd joint IEEE international workshop on. IEEE, pp 65\u201372","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"9473_CR14","doi-asserted-by":"crossref","unstructured":"Efros A, Berg AC, Mori G, Malik J (2003) Recognizing action at a distance. In: Computer vision, 2003. Proceedings. Ninth IEEE international conference on. IEEE, pp 726\u2013733","DOI":"10.1109\/ICCV.2003.1238420"},{"key":"9473_CR15","doi-asserted-by":"crossref","unstructured":"Fossati A, Dimitrijevic M, Lepetit V, Fua P (2007) Bridging the gap between detection and tracking for 3D monocular video-based motion capture. In: Computer vision and pattern recognition, 2007. CVPR\u201907. IEEE conference on. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383297"},{"key":"9473_CR16","doi-asserted-by":"crossref","unstructured":"Gao Y, Wang T, Li J, Du Y, Hu W, Zhang Y, Ai H (2007) Cast indexing for videos by ncuts and page ranking. In: Proceedings of the 6th ACM international conference on Image and video retrieval. ACM, pp 441\u2013447","DOI":"10.1145\/1282280.1282345"},{"issue":"13","key":"9473_CR17","doi-asserted-by":"crossref","first-page":"5472","DOI":"10.1016\/j.eswa.2015.03.010","volume":"42","author":"I G\u00f3mez-Conde","year":"2015","unstructured":"G\u00f3mez-Conde I, Olivieri DN (2015) A KPCA spatio-temporal differential geometric trajectory cloud classifier for recognizing human actions in a CBVR system. Expert Syst Appl 42(13):5472\u20135490","journal-title":"Expert Syst Appl"},{"issue":"4","key":"9473_CR18","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1007\/s10462-012-9341-3","volume":"42","author":"D Gowsikhaa","year":"2014","unstructured":"Gowsikhaa D, Abirami S, Baskaran R (2014) Automated human behavior analysis from surveillance videos: a survey. Artif Intell Rev 42(4):747\u2013765","journal-title":"Artif Intell Rev"},{"issue":"3","key":"9473_CR19","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1016\/j.patcog.2010.08.022","volume":"44","author":"R Ji","year":"2011","unstructured":"Ji R, Yao H, Sun X (2011) Actor-independent action search using spatiotemporal vocabulary with appearance hashing. Pattern Recognit 44(3):624\u2013638","journal-title":"Pattern Recognit"},{"issue":"5","key":"9473_CR20","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/TCSVT.2011.2129870","volume":"21","author":"YG Jiang","year":"2011","unstructured":"Jiang YG, Li Z, Chang SF (2011) Modeling scene and object contexts for human action retrieval with few examples. IEEE Trans Circuits Syst Video Technol 21(5):674\u2013681","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"9473_CR21","doi-asserted-by":"crossref","unstructured":"Jones S, Shao L (2011) Action retrieval with relevance feedback on YouTube videos. In: Proceedings of the third international conference on internet multimedia computing and service. ACM, pp 42\u201345","DOI":"10.1145\/2043674.2043687"},{"key":"9473_CR22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.ins.2013.02.018","volume":"236","author":"S Jones","year":"2013","unstructured":"Jones S, Shao L (2013) Content-based retrieval of human actions from realistic video databases. Inf Sci 236:56\u201365","journal-title":"Inf Sci"},{"key":"9473_CR23","doi-asserted-by":"crossref","unstructured":"Jones S, Shao L (2014) A multigraph representation for improved unsupervised\/semi-supervised learning of human actions. In: Computer vision and pattern recognition (CVPR), 2014 IEEE conference on. IEEE, pp 820\u2013826","DOI":"10.1109\/CVPR.2014.110"},{"key":"9473_CR24","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.neucom.2013.07.031","volume":"124","author":"S Jones","year":"2014","unstructured":"Jones S, Shao L, Du K (2014) Active learning for human action retrieval using query pool selection. Neurocomputing 124:89\u201396","journal-title":"Neurocomputing"},{"issue":"4","key":"9473_CR25","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.patrec.2011.05.001","volume":"33","author":"S Jones","year":"2012","unstructured":"Jones S, Shao L, Zhang J, Liu Y (2012) Relevance feedback for real-world human action retrieval. Pattern Recognit Lett 33(4):446\u2013452","journal-title":"Pattern Recognit Lett"},{"key":"9473_CR26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-88688-4_22","volume-title":"Cross-view action recognition from temporal self-similarities","author":"IN Junejo","year":"2008","unstructured":"Junejo IN, Dexter E, Laptev I, P\u00e9rez P (2008) Cross-view action recognition from temporal self-similarities. Springer, Berlin Heidelberg"},{"issue":"1","key":"9473_CR27","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2010.68","volume":"33","author":"IN Junejo","year":"2011","unstructured":"Junejo IN, Dexter E, Laptev I, Perez P (2011) View-independent action recognition from temporal self-similarities. IEEE Trans Pattern Anal Mach Intell 33(1):172\u2013185","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9473_CR28","doi-asserted-by":"crossref","unstructured":"Kehl R, Bray M, Van Gool L (2005) Full body tracking from multiple views using stochastic sampling. In: Computer vision and pattern recognition, 2005. CVPR 2005. IEEE computer society conference on. IEEE, vol 2, pp 129\u2013136","DOI":"10.1109\/CVPR.2005.165"},{"key":"9473_CR29","doi-asserted-by":"crossref","unstructured":"Klaser A, Marsza\u0142ek M, Schmid C (2008) A spatio-temporal descriptor based on 3d-gradients. In: BMVC 2008-19th British machine vision conference. British machine vision association, pp 275:1","DOI":"10.5244\/C.22.99"},{"key":"9473_CR30","doi-asserted-by":"crossref","unstructured":"Kl\u00e4ser A, Marsza\u0142ek M, Schmid C, Zisserman A (2012) Human focused action localization in video. In: Trends and topics in computer vision. Springer, Berlin Heidelberg, pp 219\u2013233","DOI":"10.1007\/978-3-642-35749-7_17"},{"issue":"2\u20133","key":"9473_CR31","doi-asserted-by":"crossref","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":"9473_CR32","doi-asserted-by":"crossref","unstructured":"Laptev I, Lindeberg T (2005) Space-time interest points. In: Computer vision, 2003. IEEE conference on. IEEE","DOI":"10.1007\/s11263-005-1838-7"},{"key":"9473_CR33","doi-asserted-by":"crossref","unstructured":"Laptev I, Marsza\u0142ek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: Computer vision and pattern recognition, 2008. CVPR 2008. IEEE conference on. IEEE, pp 1-8","DOI":"10.1109\/CVPR.2008.4587756"},{"issue":"1","key":"9473_CR34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1126004.1126005","volume":"2","author":"MS Lew","year":"2006","unstructured":"Lew MS, Sebe N, Djeraba C, Jain R (2006) Content-based multimedia information retrieval: state of the art and challenges. ACM Trans Multimed Comput Commun Appl (TOMM) 2(1):1\u201319","journal-title":"ACM Trans Multimed Comput Commun Appl (TOMM)"},{"issue":"11","key":"9473_CR35","doi-asserted-by":"crossref","first-page":"3597","DOI":"10.1109\/TIP.2006.881938","volume":"15","author":"J Li","year":"2006","unstructured":"Li J, Allinson N, Tao D, Li X (2006) Multitraining support vector machine for image retrieval. IEEE Trans Image Process 15(11):3597\u20133601","journal-title":"IEEE Trans Image Process"},{"key":"9473_CR36","unstructured":"Li R, Zickler T (2012) Discriminative virtual views for cross-view action recognition. In: Computer vision and pattern recognition (CVPR), 2012 IEEE conference on. IEEE, pp 2855\u20132862"},{"key":"9473_CR37","doi-asserted-by":"crossref","unstructured":"Lin Z, Jiang Z, Davis LS (2009) Recognizing actions by shape-motion prototype trees. In: Computer vision, 2009 IEEE 12th international conference on. IEEE, pp 444\u2013451","DOI":"10.1109\/ICCV.2009.5459184"},{"key":"9473_CR38","doi-asserted-by":"crossref","unstructured":"Liu D, Hua XS, Yang L, Wang M, Zhang HJ (2009). Tag ranking. In: Proceedings of the 18th international conference on world wide web. ACM, pp 351\u2013360","DOI":"10.1145\/1526709.1526757"},{"key":"9473_CR39","doi-asserted-by":"crossref","unstructured":"Liu J, Shah M, Kuipers B, Savarese S (2011) Cross-view action recognition via view knowledge transfer. In: Computer vision and pattern recognition (CVPR), 2011 IEEE conference on. IEEE, pp 3209\u20133216","DOI":"10.1109\/CVPR.2011.5995729"},{"key":"9473_CR40","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.neucom.2014.12.120","volume":"173","author":"L Liu","year":"2016","unstructured":"Liu L, Bai X, Zhang H, Zhou J, Tang W (2016) Describing and learning of related parts based on latent structural model in big data. Neurocomputing 173:355\u2013363","journal-title":"Neurocomputing"},{"key":"9473_CR41","doi-asserted-by":"crossref","unstructured":"Liu L, Shao L, Li X, Lu K (2015) Learning spatio-temporal representations for action recognition: a genetic programming approach","DOI":"10.1109\/TCYB.2015.2399172"},{"key":"9473_CR42","doi-asserted-by":"crossref","first-page":"3819","DOI":"10.1016\/j.patcog.2014.07.006","volume":"47","author":"L Liu","year":"2014","unstructured":"Liu L, Shao L, Zheng F, Li X (2014) Realistic action recognition via sparsely-constructed Gaussian processes. Pattern Recognit 47:3819\u20133827","journal-title":"Pattern Recognit"},{"key":"9473_CR43","doi-asserted-by":"crossref","unstructured":"Liu X, Yibo L (2014) Research on human action recognition based on global and local mixed features. In: International conference on mechatronics, control and electronic engineering","DOI":"10.2991\/mce-14.2014.175"},{"issue":"2","key":"9473_CR44","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"9473_CR45","doi-asserted-by":"crossref","unstructured":"Menier C, Boyer E, Raffin B (2006). 3d skeleton-based body pose recovery. In: 3rd international symposium on 3D data processing, visualization and transmission (DPVT\u201906). IEEE computer society, pp 389\u2013396","DOI":"10.1109\/3DPVT.2006.7"},{"key":"9473_CR46","doi-asserted-by":"crossref","unstructured":"Mikolajczyk K, Schmid C (2002) An affine invariant interest point detector. In: Computer vision\u2014ECCV 2002. Springer, Berlin Heidelberg, pp 128\u2013142","DOI":"10.1007\/3-540-47969-4_9"},{"key":"9473_CR47","doi-asserted-by":"crossref","unstructured":"Mikolajczyk K, Uemura H (2008) Action recognition with motion-appearance vocabulary forest. In: Computer vision and pattern recognition, 2008. CVPR 2008. IEEE conference on. IEEE, pp 1-8","DOI":"10.1109\/CVPR.2008.4587628"},{"key":"9473_CR48","doi-asserted-by":"crossref","unstructured":"Paez F, Vanegas J, Gonzalez F (2013) An evaluation of NMF algorithm on human action video retrieval. In: Image, signal processing, and artificial vision (STSIVA), 2013 XVIII symposium of. IEEE, pp 1\u20134","DOI":"10.1109\/STSIVA.2013.6644926"},{"key":"9473_CR49","doi-asserted-by":"crossref","unstructured":"Paez F, Vanegas J, Gonzalez F (2014) Online multimodal matrix factorization for human action video indexing. In: Content-based multimedia indexing (CBMI), 2014 12th international workshop on. IEEE, pp 1\u20136","DOI":"10.1109\/CBMI.2014.6849823"},{"issue":"3","key":"9473_CR50","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1023\/A:1007975200487","volume":"23","author":"R Polana","year":"1997","unstructured":"Polana R, Nelson RC (1997) Detection and recognition of periodic, nonrigid motion. Int J Comput Vis 23(3):261\u2013282","journal-title":"Int J Comput Vis"},{"issue":"6","key":"9473_CR51","doi-asserted-by":"crossref","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":"9473_CR52","unstructured":"Ramezani M, Yaghmaee F (2014a) Content-based retrieval of human actions by extracting the main moving directions and their scales. In: 4th international conference on information technology management, communication and computer, Iran, Tehran"},{"key":"9473_CR53","unstructured":"Ramezani M, Yaghmaee F (2014b) Using the fuzzy clustering algorithm to improve the content-based action retrieval. In: 14\u2019th Iranian conference on fuzzy systems"},{"key":"9473_CR54","doi-asserted-by":"crossref","unstructured":"Ramezani M, Yaghmaee F (2014c) Content-based retrieval of human actions by analysing the statistical information of features. In: Information and knowledge technology (IKT), 2014 6th conference on. IEEE, pp 56\u201360","DOI":"10.1109\/IKT.2014.7030333"},{"key":"9473_CR55","doi-asserted-by":"crossref","unstructured":"Ramezani M, Yaghmaee F (2014d) Content-based human actions retrieval by a novel low complex action representation. In: Computer and knowledge engineering (ICCKE), 2014 4th international econference on. IEEE, pp 204\u2013208","DOI":"10.1109\/ICCKE.2014.6993466"},{"key":"9473_CR56","doi-asserted-by":"crossref","unstructured":"Reddy KK, Liu J, Shah M (2009, September) Incremental action recognition using feature-tree. In:\u00a0Computer vision, 2009 IEEE 12th international conference on. IEEE, pp 1010\u20131017","DOI":"10.1109\/ICCV.2009.5459374"},{"key":"9473_CR57","doi-asserted-by":"crossref","unstructured":"Sch\u00fcldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local SVM approach. In: Pattern recognition, 2004. ICPR 2004. Proceedings of the 17th international conference on. IEEE, vol 3, pp 32\u201336","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"9473_CR58","doi-asserted-by":"crossref","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th international conference on multimedia. ACM, pp 357\u2013360","DOI":"10.1145\/1291233.1291311"},{"key":"9473_CR59","doi-asserted-by":"crossref","unstructured":"Shao L, Chen X (2010) Histogram of body poses and spectral regression discriminant analysis for human action categorization. In: BMVC, pp 1\u201311","DOI":"10.5244\/C.24.88"},{"issue":"3","key":"9473_CR60","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1109\/TCSVT.2013.2276700","volume":"24","author":"L Shao","year":"2014","unstructured":"Shao L, Jones S, Li X (2014) Efficient search and localization of human actions in video databases. IEEE Trans Circuits Syst Video Technol 24(3):504\u2013512","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"9473_CR61","unstructured":"Shao L, Liu L, Yu M (2015) Kernelized multiview projection for robust action recognition. Int J Comput Vis, 1\u201315"},{"key":"9473_CR62","doi-asserted-by":"crossref","unstructured":"Shao L, Wu D, Chen X (2011) Action recognition using correlogram of body poses and spectral regression. In: Image processing (ICIP), 2011 18th IEEE international conference on. IEEE, pp 209\u2013212","DOI":"10.1109\/ICIP.2011.6116023"},{"issue":"6","key":"9473_CR63","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1109\/TCYB.2013.2273174","volume":"44","author":"L Shao","year":"2014","unstructured":"Shao L, Zhen X, Tao D, Li X (2014) Spatio-temporal Laplacian pyramid coding for action recognition. IEEE Trans Cybern 44(6):817\u2013827","journal-title":"IEEE Trans Cybern"},{"issue":"5","key":"9473_CR64","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1016\/j.ipm.2005.11.003","volume":"42","author":"AF Smeaton","year":"2006","unstructured":"Smeaton AF, Browne P (2006) A usage study of retrieval modalities for video shot retrieval. Inf Process Manag 42(5):1330\u20131344","journal-title":"Inf Process Manag"},{"key":"9473_CR65","doi-asserted-by":"crossref","unstructured":"Sun X, Yao H, Liu T, Xu P, Liu X (2008) Place retrieval with graph-view model. In: ACM conference on multimedia information retrieval","DOI":"10.1145\/1460096.1460141"},{"key":"9473_CR66","doi-asserted-by":"crossref","unstructured":"Tang J, Shao L, Zhen X (2013) Human action retrieval via efficient feature matching. In: Advanced video and signal based surveillance (AVSS), 2013 10th IEEE international conference on. IEEE, pp 306\u2013311","DOI":"10.1109\/AVSS.2013.6636657"},{"key":"9473_CR67","doi-asserted-by":"crossref","unstructured":"Thi TH, Zhang J, Cheng L, Wang L, Satoh S (2010) Human action recognition and localization in video using structured learning of local space-time features. In: Advanced video and signal based surveillance (AVSS), 2010 seventh IEEE international conference on. IEEE, pp 204\u2013211","DOI":"10.1109\/AVSS.2010.76"},{"key":"9473_CR68","doi-asserted-by":"crossref","unstructured":"Tong S, Chang E (2001) Support vector machine active learning for image retrieval. In: Proceedings of the ninth ACM international conference on multimedia. ACM, pp 107\u2013118","DOI":"10.1145\/500141.500159"},{"key":"9473_CR69","unstructured":"Typke R, Wiering F, Veltkamp RC (2005). A survey of music information retrieval systems. In: ISMIR, pp 153\u2013160"},{"key":"9473_CR70","doi-asserted-by":"crossref","unstructured":"Wang H, Zheng X, Xiao B (2015) Large-scale human action recognition with spark. In: Multimedia signal processing (MMSP), 2015 IEEE 17th international workshop on. IEEE, pp 1\u20136","DOI":"10.1109\/MMSP.2015.7340818"},{"issue":"1","key":"9473_CR71","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/JPROC.2015.2487976","volume":"104","author":"J Wang","year":"2016","unstructured":"Wang J, Liu W, Kumar S, Chang SF (2016) Learning to Hash for indexing big data\u2013a survey. Proc IEEE 104(1):34\u201357","journal-title":"Proc IEEE"},{"issue":"4","key":"9473_CR72","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1109\/TMM.2012.2185041","volume":"14","author":"M Wang","year":"2012","unstructured":"Wang M, Hong R, Li G, Zha ZJ, Yan S, Chua TS (2012) Event driven web video summarization by tag localization and key-shot identification. IEEE Trans Multimed 14(4):975\u2013985","journal-title":"IEEE Trans Multimed"},{"issue":"3","key":"9473_CR73","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TPAMI.2012.124","volume":"35","author":"L Wu","year":"2013","unstructured":"Wu L, Jin R, Jain AK (2013) Tag completion for image retrieval. IEEE Trans Pattern Anal Mach Intell 35(3):716\u2013727","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9473_CR74","doi-asserted-by":"crossref","unstructured":"Yamato J, Ohya J, Ishii K (1992) Recognizing human action in time-sequential images using hidden markov model. In: Computer vision and pattern recognition, 1992. Proceedings CVPR\u201992., 1992 IEEE computer society conference on. IEEE, pp 379\u2013385","DOI":"10.1109\/CVPR.1992.223161"},{"key":"9473_CR75","doi-asserted-by":"crossref","unstructured":"Yan R, Hauptmann AG, Jin R (2003) Negative pseudo-relevance feedback in content-based video retrieval. In: Proceedings of the eleventh ACM international conference on Multimedia. ACM, pp 343\u2013346","DOI":"10.1145\/957013.957087"},{"issue":"2","key":"9473_CR76","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.cviu.2006.07.012","volume":"104","author":"A Yilmaz","year":"2006","unstructured":"Yilmaz A, Shah M (2006) Matching actions in presence of camera motion. Comput Vis Image Underst 104(2):221\u2013231","journal-title":"Comput Vis Image Underst"},{"issue":"3","key":"9473_CR77","doi-asserted-by":"crossref","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"},{"key":"9473_CR78","doi-asserted-by":"crossref","unstructured":"Yu G, Yuan J, Liu Z (2011) Real-time human action search using random forest based hough voting. In: Proceedings of the 19th ACM international conference on Multimedia. ACM, pp 1149\u20131152","DOI":"10.1145\/2072298.2071961"},{"key":"9473_CR79","doi-asserted-by":"crossref","unstructured":"Yu G, Yuan J, Liu Z (2011) Unsupervised random forest indexing for fast action search. In: Computer vision and pattern recognition (CVPR), 2011 IEEE conference on. IEEE, pp 865\u2013872","DOI":"10.1109\/CVPR.2011.5995488"},{"key":"9473_CR80","doi-asserted-by":"crossref","unstructured":"Yu G, Yuan J, Liu Z (2015) Unsupervised trees for human action search. In: Human action analysis with randomized trees. Springer Singapore, pp 29\u201356","DOI":"10.1007\/978-981-287-167-1_3"},{"issue":"9","key":"9473_CR81","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.1109\/TPAMI.2011.38","volume":"33","author":"J Yuan","year":"2011","unstructured":"Yuan J, Liu Z, Wu Y (2011) Discriminative video pattern search for efficient action detection. IEEE Trans Pattern Anal Mach Intell 33(9):1728\u20131743","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"9473_CR82","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/s00530-012-0297-6","volume":"19","author":"X Zhai","year":"2013","unstructured":"Zhai X, Peng Y, Xiao J (2013) Cross-media retrieval by intra-media and inter-media correlation mining. Multimed Syst 19(5):395\u2013406","journal-title":"Multimed Syst"},{"issue":"4","key":"9473_CR83","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1016\/S0031-3203(96)00109-4","volume":"30","author":"HJ Zhang","year":"1997","unstructured":"Zhang HJ, Wu J, Zhong D, Smoliar SW (1997) An integrated system for content-based video retrieval and browsing. Pattern Recognit 30(4):643\u2013658","journal-title":"Pattern Recognit"},{"key":"9473_CR84","doi-asserted-by":"crossref","unstructured":"Zhang Z, Wang C, Xiao B, Zhou W, Liu S, Shi C (2013) Cross-view action recognition via a continuous virtual path. In: Computer vision and pattern recognition (CVPR), 2013 IEEE conference on. IEEE, pp 2690\u20132697","DOI":"10.1109\/CVPR.2013.347"},{"key":"9473_CR85","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/j.neucom.2014.03.092","volume":"151","author":"S Zhao","year":"2015","unstructured":"Zhao S, Chen L, Yao H, Zhang Y, Sun X (2015) Strategy for dynamic 3D depth data matching towards robust action retrieval. Neurocomputing 151:533\u2013543","journal-title":"Neurocomputing"},{"issue":"7","key":"9473_CR86","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.1109\/TCSVT.2013.2240916","volume":"23","author":"X Zhen","year":"2013","unstructured":"Zhen X, Shao L, Tao D, Li X (2013) Embedding motion and structure features for action recognition. IEEE Trans Circuits Syst Video Technol 23(7):1182\u20131190","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"1\u20132","key":"9473_CR87","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/s11263-014-0703-y","volume":"109","author":"F Zhu","year":"2014","unstructured":"Zhu F, Shao L (2014) Weakly-supervised cross-domain dictionary learning for visual recognition. Int J Comput Vis 109(1\u20132):42\u201359","journal-title":"Int J Comput Vis"},{"issue":"1","key":"9473_CR88","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.patrec.2012.04.016","volume":"34","author":"F Zhu","year":"2013","unstructured":"Zhu F, Shao L, Lin M (2013) Multi-view action recognition using local similarity random forests and sensor fusion. Pattern Recognit Lett 34(1):20\u201324","journal-title":"Pattern Recognit Lett"},{"issue":"3","key":"9473_CR89","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s11704-011-0080-4","volume":"5","author":"X Zhu","year":"2011","unstructured":"Zhu X, Liu Z (2011) Human behavior clustering for anomaly detection. Front Comput Sci China 5(3):279\u2013289","journal-title":"Front Comput Sci China"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9473-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-016-9473-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9473-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9473-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,5]],"date-time":"2019-09-05T18:30:11Z","timestamp":1567708211000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-016-9473-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,15]]},"references-count":89,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["9473"],"URL":"https:\/\/doi.org\/10.1007\/s10462-016-9473-y","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3,15]]}}}