乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T19:18:40Z","timestamp":1721675920329},"reference-count":253,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1016\/j.cviu.2015.10.010","type":"journal-article","created":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T13:55:20Z","timestamp":1459518920000},"page":"73-105","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":20,"special_numbering":"C","title":["From pose to activity: Surveying datasets and introducing CONVERSE"],"prefix":"10.1016","volume":"144","author":[{"given":"Michael","family":"Edwards","sequence":"first","affiliation":[]},{"given":"Jingjing","family":"Deng","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2701-8660","authenticated-orcid":false,"given":"Xianghua","family":"Xie","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2015.10.010_bib0001","unstructured":"Swansea University Computer Vision and Medical Image Analysis Group, CONVERSE dataset. Available at: http:\/\/csvision.swan.ac.uk\/converse (accessed 29.07.15)."},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0002","doi-asserted-by":"crossref","first-page":"201","DOI":"10.3758\/BF03212378","article-title":"Visual perception of biological motion and a model for its analysis","volume":"14","author":"Johansson","year":"1973","journal-title":"Percept. Psychophys."},{"key":"10.1016\/j.cviu.2015.10.010_bib0003","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1038\/scientificamerican0675-76","article-title":"Visual motion perception","volume":"232","author":"Johansson","year":"1975","journal-title":"Sci. Am."},{"key":"10.1016\/j.cviu.2015.10.010_bib0004","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1098\/rspb.1978.0020","article-title":"Representation and recognition of the spatial organization of three-dimensional shapes","volume":"200","author":"Marr","year":"1978","journal-title":"Proc. R. Soc. Lond. Ser. B. Containing Papers of a Biological Character."},{"issue":"6","key":"10.1016\/j.cviu.2015.10.010_bib0005","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TPAMI.1980.6447705","article-title":"Towards a system for the interpretation of moving light displays","volume":"2","author":"Rashid","year":"1980","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0006","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/0262-8856(83)90003-3","article-title":"Model-based vision: a program to see a walking person","volume":"1","author":"Hogg","year":"1983","journal-title":"Image Vis. Comput."},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0007","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/0734-189X(85)90094-5","article-title":"Determination of 3D human body postures from a single view","volume":"30","author":"Lee","year":"1984","journal-title":"Comput. Vis. Graph. Image Process."},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0008","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/21.148408","article-title":"Knowledge-guided visual perception of 3-D human gait from a single image sequence","volume":"22","author":"Chen","year":"1992","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"10.1016\/j.cviu.2015.10.010_bib0009","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1006\/ciun.1994.1006","article-title":"Towards model-based recognition of human movement in image sequences","volume":"59","author":"Rohr","year":"1994","journal-title":"CVGIP: Image Underst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0010","series-title":"Proceedings of IEEE Workshop on Motion of Non-Rigid and Articulated Objects","first-page":"2","article-title":"Articulated and elastic non-rigid motion: a review","author":"Aggarwal","year":"1994"},{"key":"10.1016\/j.cviu.2015.10.010_bib0011","series-title":"Proceedings of the International Conference on Computer Vision","first-page":"624","article-title":"Recognition of human body motion using phase space constraints","author":"Campbell","year":"1995"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0012","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1006\/cviu.1998.0744","article-title":"Human motion analysis: a review","volume":"73","author":"Aggarwal","year":"1999","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0013","series-title":"Proceedings of the IEEE Workshop on Motion of Non-Rigid and Articulated Objects","first-page":"77","article-title":"Low level recognition of human motion (or how to get your man without finding his body parts)","author":"Polana","year":"1994"},{"key":"10.1016\/j.cviu.2015.10.010_bib0014","series-title":"Proceedings of International Conference on Intelligent Robots and System","first-page":"2139","article-title":"Recognition of human body motions by robots","author":"Osaka","year":"1992"},{"key":"10.1016\/j.cviu.2015.10.010_bib0015","first-page":"212","article-title":"Tracking and counting moving people","volume":"3","author":"Rossi","year":"1994","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2015.10.010_bib0016","series-title":"Proceedings of International Conference on Pattern Recognition","first-page":"627","article-title":"Real-time self-calibrating stereo person tracking using 3-D shape estimation from blob features","volume":"vol.\u00a03","author":"Azarbayejani","year":"1996"},{"issue":"7","key":"10.1016\/j.cviu.2015.10.010_bib0017","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1109\/34.598236","article-title":"Pfinder: Real-time tracking of the human body","volume":"19","author":"Wren","year":"1997","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0018","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Recognizing human action in time-sequential images using hidden markov model","author":"Yamato","year":"1992"},{"key":"10.1016\/j.cviu.2015.10.010_bib0019","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"0","article-title":"Probabilistic recognition of activity using local appearance","author":"Chomat","year":"1999"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0020","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/34.910878","article-title":"The recognition of human movement using temporal templates","volume":"23","author":"Bobick","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0021","series-title":"Proceedings of International Conference on Computer Vision","first-page":"432","article-title":"Space-time interest points","volume":"vol. 1","author":"Laptev","year":"2003"},{"key":"10.1016\/j.cviu.2015.10.010_bib0022","series-title":"Proceedings of International Conference on Pattern Recognition","first-page":"3","article-title":"Recognizing human actions : a local SVM approach","author":"Schuldt","year":"2004"},{"key":"10.1016\/j.cviu.2015.10.010_bib0023","series-title":"IEEE Int. Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","first-page":"65","article-title":"Behavior recognition via sparse spatio-temporal features","author":"Dollar","year":"2005"},{"issue":"12","key":"10.1016\/j.cviu.2015.10.010_bib0024","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","article-title":"Actions as space-time shapes","volume":"29","author":"Blank","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0025","series-title":"Proceedings of International Conference on Computer Vision Workshops, October 2005","first-page":"2008","article-title":"What are they doing?: collective activity classification using spatio-temporal relationship among people","volume":"vol. 24","author":"Choi","year":"2008"},{"issue":"6","key":"10.1016\/j.cviu.2015.10.010_bib0026","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1016\/j.cviu.2013.01.013","article-title":"A survey of video datasets for human action and activity recognition","volume":"117","author":"Chaquet","year":"2013","journal-title":"Comp. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0027","series-title":"Proceedings of the British Conference on Machine Vision","first-page":"67.1","article-title":"Does human action recognition benefit from pose estimation?","author":"Yao","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0028","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"20","article-title":"View invariant human action recognition using histograms of 3D joints","author":"Xia","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0029","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"716","article-title":"Hon4d:hHistogram of oriented 4d normals for activity recognition from depth sequences","author":"Oreifej","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0030","series-title":"Proceedings of Workshop on Applications of Computer Vision","first-page":"53","article-title":"Berkeley MHAD: a comprehensive multimodal human action database","author":"Ofli","year":"2013"},{"issue":"4","key":"10.1016\/j.cviu.2015.10.010_bib0031","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1109\/TSMCA.2012.2226575","article-title":"Realistic human action recognition with multimodal feature selection and fusion","volume":"43","author":"Wu","year":"2013","journal-title":"IEEE Trans. Syst. Man Cybern. Part A: Syst. Humans"},{"issue":"1","key":"10.1016\/j.cviu.2015.10.010_bib0032","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s12193-014-0150-7","article-title":"An audio\u2013visual dataset of human-human interactions in stressful situations","volume":"8","author":"Lefter","year":"2014","journal-title":"Journal on Multimodal User Interfaces"},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0033","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.cviu.2010.10.002","article-title":"A survey of vision-based methods for action representation, segmentation and recognition","volume":"115","author":"Weinland","year":"2011","journal-title":"Comp. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0034","series-title":"Technical report","article-title":"Kinect depth sensor evaluation for computer vision applications","author":"Andersen","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0035","series-title":"Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications","first-page":"257","article-title":"A state of the art report on kinect sensor setups in computer vision","author":"Berger","year":"2013"},{"issue":"5","key":"10.1016\/j.cviu.2015.10.010_bib0036","doi-asserted-by":"crossref","first-page":"1318","DOI":"10.1109\/TCYB.2013.2265378","article-title":"Enhanced computer vision with Microsoft Kinect sensor: a review","volume":"43","author":"Han","year":"2013","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.cviu.2015.10.010_bib0037","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"28","article-title":"Two-person interaction detection using body-pose features and multiple instance learning","author":"Yun","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0038","series-title":"Proceedings of IEEE International Symposium on Signal Process. and Information Technology","first-page":"263","article-title":"Robust classification of human actions from 3D data","author":"Huynh","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0039","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"486","article-title":"Fusing spatiotemporal features and joints for 3D action recognition","author":"Zhu","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0040","series-title":"Proceedings of IEEE International Workshop on CVPR for Human Communicative Behavior Analysis","article-title":"Action recognition based on a bag of 3D points","author":"Li","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0041","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1290","article-title":"Mining actionlet ensemble for action recognition with depth cameras","author":"Wang","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0042","series-title":"Technical Report","article-title":"Aligned cluster analysis for temporal segmentation of human motion","author":"Zhou","year":"2008"},{"key":"10.1016\/j.cviu.2015.10.010_bib0043","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"915","article-title":"An approach to pose-based action recognition","author":"Wang","year":"2013"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0044","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1109\/TPAMI.2012.137","article-title":"Hierarchical aligned cluster analysis for temporal clustering of human motion","volume":"35","author":"Zhou","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0045","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1109\/TAMD.2014.2315676","article-title":"Adaptive human action recognition with an evolving bag of key poses","volume":"6","author":"Chaaraoui","year":"2014","journal-title":"Auton. Ment. Dev."},{"key":"10.1016\/j.cviu.2015.10.010_bib0046","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"613","article-title":"View invariants for human action recognition","volume":"2","author":"Parameswaran","year":"2003"},{"key":"10.1016\/j.cviu.2015.10.010_bib0047","series-title":"Human Behavior Understanding","first-page":"29","article-title":"An efficient approach for multi-view human action recognition based on bag-of-key-poses","author":"Chaaraoui","year":"2012"},{"issue":"15","key":"10.1016\/j.cviu.2015.10.010_bib0048","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1016\/j.patrec.2013.01.021","article-title":"Silhouette-based human action recognition using sequences of key poses","volume":"34","author":"Chaaraoui","year":"2013","journal-title":"Pattern Recognit. Lett."},{"issue":"1","key":"10.1016\/j.cviu.2015.10.010_bib0049","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","article-title":"Dynamic programming algorithm optimization for spoken word recognition","volume":"26","author":"Sakoe","year":"1978","journal-title":"IEEE Trans. Acoustics Speech Signal Process."},{"key":"10.1016\/j.cviu.2015.10.010_bib0050","series-title":"Proceedings of International Conference on Computer Vision","first-page":"236","article-title":"Multi-scale gesture recognition from time-varying contours","volume":"vol. \u00a01","author":"Li","year":"2005"},{"key":"10.1016\/j.cviu.2015.10.010_bib0051","first-page":"17","article-title":"Using dynamic programming to match human behavior sequences","author":"Chen","year":"2008","journal-title":"Control, Automation, Robotics and Vision"},{"key":"10.1016\/j.cviu.2015.10.010_bib0052","series-title":"Proceedings of International Conference on Intelligent Computer Communication and Processing","first-page":"127","article-title":"Action recognition based on fast dynamic-time warping method","author":"Vajda","year":"2009"},{"issue":"10","key":"10.1016\/j.cviu.2015.10.010_bib0053","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1109\/TPAMI.2009.41","article-title":"View-invariant action recognition from point triplets","volume":"31","author":"Shen","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0054","series-title":"Proceedings of International Conference on Electrical Engineering and Informatics","article-title":"Human action recognition using dynamic time warping","author":"Sempena","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0055","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Action recognition using exemplar-based embedding","author":"Weinland","year":"2008"},{"key":"10.1016\/j.cviu.2015.10.010_bib0056","series-title":"Proceedings of International Congress on Image and Signal Process.","first-page":"404","article-title":"Learning a similarity metric discriminatively for pose exemplar based action recognition","author":"Wang","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0057","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"245","article-title":"A critical review of action recognition benchmarks","author":"Hassner","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0058","unstructured":"S. Stein, S.J. McKenna, 50 Salads dataset. Available at: http:\/\/cvip.computing.dundee.ac.uk\/datasets\/foodpreparation\/50salads\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0059","series-title":"Proceedings of International Joint Conference on Pervasive and Ubiquitous Computing","article-title":"Combining embedded accelerometers with computer vision for recognizing food preparation activities","author":"Stein","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0060","unstructured":"S.J. Blunsden, R.B. Fisher, BEHAVE interactions test case scenarios. Available at: http:\/\/groups.inf.ed.ac.uk\/vision\/BEHAVEDATA\/INTERACTIONS\/ (accessed 29.07.15)."},{"issue":"4","key":"10.1016\/j.cviu.2015.10.010_bib0061","first-page":"1","article-title":"The BEHAVE video dataset : ground truthed video for multi-person behavior classification","volume":"210","author":"Blunsden","year":"2010","journal-title":"Ann. BMVA"},{"key":"10.1016\/j.cviu.2015.10.010_bib0062","unstructured":"F. Ofli, R. Chaudhry, G. Kurillo, R. Vidal, R. Bajcsy, Berkeley Multimodal Human Action Database. Available at: http:\/\/tele-immersion.citris-uc.org\/berkeley mhad (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0063","unstructured":"Y. Kong, Y. Jia, Y. Fu, BIT-Interaction dataset. Available at: https:\/\/sites.google.com\/site\/alexkongy\/software (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0064","series-title":"Proceedings of European Conference on Computer Vision","first-page":"300","article-title":"Learning human interaction by interactive phrases","volume":"vol. 7572","author":"Kong","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0065","unstructured":"Cornell University, Cornell Activity Datasets CAD-60, CAD-120. Available at: http:\/\/pr.cs.cornell.edu\/humanactivities\/data.php (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0066","series-title":"Proceedings of International Conference on Robotics and Automation","article-title":"Unstructured human activity detection from RGBD images","author":"Sung","year":"2012"},{"issue":"8","key":"10.1016\/j.cviu.2015.10.010_bib0067","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1177\/0278364913478446","article-title":"Learning human activities and object affordances from RGB-D videos","volume":"32","author":"Koppula","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.cviu.2015.10.010_bib0068","unstructured":"Institute of Automation Chinese Academy of Sciences, CASIA action database for recognition. Available at: http:\/\/www.cbsr.ia.ac.cn\/english\/Action 20Databases%20EN.asp (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0069","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1109\/TSMCB.2008.2011815","article-title":"View-independent behavior analysis","volume":"39","author":"Huang","year":"2009","journal-title":"IEEE Trans Syst. Man Cybern."},{"key":"10.1016\/j.cviu.2015.10.010_bib0070","unstructured":"R. Fisher, CAVIAR test case scenarios. Available at: http:\/\/groups.inf.ed.ac.uk\/vision\/CAVIAR\/CAVIARDATA1\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0071","series-title":"Proceedings of International Conference on Performance Evaluation of Tracking and Surveillance","article-title":"The PETS04 surveillance ground-truth data sets","author":"Fisher","year":"2004"},{"key":"10.1016\/j.cviu.2015.10.010_bib0072","unstructured":"F. De la Torre, J. Hodgins, J. Montano, S. Valcarcel, R. Forcadam, J. Macey, Grand Challenge Data Collection, Quality of Life Technology Center. Available at: http:\/\/kitchen.cs.cmu.edu\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0073","series-title":"Technical report","article-title":"CMU-RI-TR-08-22: guide to the Carnegie Mellon University Multimodal Activity Database","author":"De la Torre","year":"2008"},{"key":"10.1016\/j.cviu.2015.10.010_bib0074","unstructured":"CMU Graphics Lab, CMU Graphics Lab Motion Capture Database. Available at: http:\/\/mocap.cs.cmu.edu\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0075","series-title":"Proceedings of Computational Visual Media Conference","article-title":"A bag of words approach to 3D human pose interaction classification with random decision forests","author":"Deng","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0076","article-title":"A bag of words approach to subject specific 3D human pose interaction classification with random decision forests","author":"Deng","year":"2013","journal-title":"Graphical Models"},{"key":"10.1016\/j.cviu.2015.10.010_bib0077","series-title":"Proceedings of International Conference on Advanced Concepts for Intelligent Vision Systems","first-page":"138","article-title":"Recognizing conversational interaction based on 3D human pose","author":"Deng","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0078","unstructured":"I. Laptev, P. P\u00e9rez, Drinking and Smoking action annotaion. Available at: http:\/\/www.di.ens.fr\/~laptev\/download.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0079","series-title":"Proceedings of International Conference on Computer Vision","article-title":"Retrieving actions in movies","author":"Laptev","year":"2007"},{"key":"10.1016\/j.cviu.2015.10.010_bib0080","unstructured":"Inria, ETISEO: video understanding evaluation. Available at: http:\/\/www-sop.inria.fr\/orion\/ETISEO\/download.htm (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0081","series-title":"Proceedings of IEEE International Conference on Advanced Video and Signal-Based Surveillance","article-title":"ETISEO, performance evaluation for video surveillance systems","author":"Nghiem","year":"2007"},{"key":"10.1016\/j.cviu.2015.10.010_bib0082","unstructured":"V. Bloom, D. Makris, V. Argyriou, G3D gaming datasets. Available at: http:\/\/dipersec.king.ac.uk\/G3D\/G3D.html."},{"key":"10.1016\/j.cviu.2015.10.010_bib0083","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"7","article-title":"G3D: a gaming action dataset and real time action recognition evaluation framework","author":"Bloom","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0084","unstructured":"V. Bloom, V. Argyriou, D. Makris, G3Di gaming datasets. Available at: http:\/\/dipersec.king.ac.uk\/G3D\/G3Di.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0085","series-title":"Proceedings of European Conference on Computer Vision","article-title":"G3Di: a gaming interaction dataset with a real time detection and evaluation framework","author":"Bloom","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0086","unstructured":"H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, T. Serre, HMDB: a large human motion database. Available at: http:\/\/serre-lab.clps.brown.edu\/resource\/hmdb-a-large-human-motion-database\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0087","series-title":"Proceedings of International Conference on Computer Vision","first-page":"2556","article-title":"HMDB: a large video database for human motion recognition","author":"Kuehne","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0088","unstructured":"I. Laptev, M. Marszaek, C. Schmid, B. Rozenfeld, Learning human actions from movies. Available at: http:\/\/www.di.ens.fr\/~laptev\/actions\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0089","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Learning realistic human actions from movies","author":"Laptev","year":"2008"},{"key":"10.1016\/j.cviu.2015.10.010_bib0090","unstructured":"M. Marszaek, I. Laptev, C. Schmid, Human actions and scenes dataset. Available at: http:\/\/www.di.ens.fr\/~laptev\/actions\/hollywood2\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0091","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2929","article-title":"Actions in context","author":"Marszalek","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0092","unstructured":"S. Hadfield, Hollywood3D. Available at: http:\/\/cvssp.org\/Hollywood3D\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0093","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3398","article-title":"Hollywood 3D: recognizing actions in 3D natural scenes","author":"Hadfield","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0094","unstructured":"L. Sigal, A.O. Balan, M.J. Black, HumanEva dataset. Available at: http:\/\/humaneva.is.tue.mpg.de\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0095","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","article-title":"Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion","volume":"87","author":"Sigal","year":"2010","journal-title":"Int. J. Comp. Vis."},{"key":"10.1016\/j.cviu.2015.10.010_bib0096","unstructured":"D. Weinland, R. Ronfard, E. Boyer, INRIA Xmas Motion Acquisition Sequences. Available at: http:\/\/4drepository.inrialpes.fr\/public\/viewgroup\/6 (accessed 29.07.15)."},{"issue":"2\u20133","key":"10.1016\/j.cviu.2015.10.010_bib0097","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.cviu.2006.07.013","article-title":"Free viewpoint action recognition using motion history volumes","volume":"104","author":"Weinland","year":"2006","journal-title":"Comp. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0098","unstructured":"M.S. Ryoo, L. Matthies, JPL First-Person Interaction dataset. Available at: http:\/\/michaelryoo.com\/jpl-interaction.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0099","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"First-Person activity recognition: what are they doing to me?","author":"Ryoo","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0100","unstructured":"K3HI dataset. Available at: http:\/\/www.lmars.whu.edu.cn\/profweb\/zhuxinyan\/DataSetPublish\/dataset.html (accessed 05.06.14)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0101","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2013\/175616","article-title":"Efficient interaction recognition through positive action representation","volume":"2013","author":"Hu","year":"2013","journal-title":"Math. Probl. Eng."},{"key":"10.1016\/j.cviu.2015.10.010_bib0102","unstructured":"I. Laptev, T. Lindeberg, Recognition of human actions. Available at: http:\/\/www.nada.kth.se\/cvap\/actions\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0103","unstructured":"C.~ Wolf, J. Mille, E. Lombardi, O. Celiktutan, M. Jiu, E. Dogan, G. Eren, M. Baccouche, E. Dellandrea, C.-E. Bichot, C. Garcia, B. Sankur, The LIRIS human activities dataset. Available at: http:\/\/liris.cnrs.fr\/voir\/activities-dataset\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0104","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.cviu.2014.06.014","article-title":"Evaluation of video activity localizations integrating quality and quantity measurements","volume":"127","author":"Wolf","year":"2014","journal-title":"Comp. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0105","unstructured":"M.P.I. for Informatics, MPI08 dataset. Available at: http:\/\/www.tnt.uni-hannover.de\/project\/MPI08 Database\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0106","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Multisensor-fusion for 3D full-body human motion capture","author":"Pons-Moll","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0107","series-title":"Proceedings of European Conference on Computer Vision","article-title":"Analyzing and evaluating markerless motion tracking using inertial sensors","author":"Baak","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0108","unstructured":"M. Rohrbach, S. Amin, M. Andriluka, B. Schiele, MPII cooking activities dataset. Available at: https:\/\/www.mpi-inf.mpg.de\/departments\/computer-vision-and-multimodal-computing\/research\/human-activity-recognition\/mpii-cooking-activities-dataset\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0109","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"A database for fine grained activity detection of cooking activities","author":"Rohrbach","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0110","unstructured":"M. Rohrbach, M. Regneri, M. Andriluka, S. Amin, M. Pinkal, B. Schiele, MPII cooking composite activities. Available at: https:\/\/www.mpi-inf.mpg.de\/departments\/computer-vision-and-multimodal-computing\/research\/human-activity-recognition\/mpii-cooking-composite-activities\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0111","series-title":"Proceedings of European Conference on Computer Vision","article-title":"Script data for attribute-based recognition of composite activities","author":"Rohrbach","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0112","unstructured":"Microsoft Research, MSR action recognition datasets and codes. Available at: http:\/\/research.microsoft.com\/en-us\/um\/people\/zliu\/actionrecorsrc\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0113","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2442","article-title":"Discriminative subvolume search for efficient action detection","author":"Yuan","year":"2009"},{"issue":"10","key":"10.1016\/j.cviu.2015.10.010_bib0114","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.1109\/TPAMI.2011.38","article-title":"Discriminative video pattern search for efficient action detection","volume":"33","author":"Yuan","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0115","series-title":"Proc. Euro. Signal Process. Conf.","first-page":"1975","article-title":"A real time system for dynamic hand gesture recognition with a depth sensor","author":"Kurakin","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0116","unstructured":"S. Singh, S. Velastin, H. Ragheb, MuHAVi: Multicamera Human Action Video dataset. Available at: dipersec.king.ac.uk\/MuHAVi-MAS\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0117","series-title":"Workshop on activity Monitoring by Multi-camera Surveillance Syst.","first-page":"48\u2014-55","article-title":"MuHAVi: a Multicamera Human Action Video dataset for the evaluation of action recognition methods","author":"Singh","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0118","unstructured":"J.C. Niebles, C.-W. Chen, L. Fei-Fei, Olympic Sports dataset. Available at: http:\/\/vision.stanford.edu\/Datasets\/OlympicSports\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0119","series-title":"Proceedings of European Conference on Computer Vision","first-page":"392","article-title":"Modeling temporal structure of decomposable motion segments for activity classification","author":"Niebles","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0120","unstructured":"C. Wallraven, M. Schultze, B. Mohler, A. Vatakis, K. Pastra, POETICON Corpus. Available at: http:\/\/poeticoncorpus.kyb.mpg.de (accessed 11.09.14)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0121","series-title":"Proceedings of IEEE Conference Automatic Face and Gesture Record Workshops","article-title":"The POETICON enacted scenario corpus: a tool for human and computational experiments on action understanding","author":"Wallraven","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0122","unstructured":"R. Messing, C. Pal, H. Kautz, University of Rochester Activities of Daily Living dataset. Available at: http:\/\/www.cs.rochester.edu\/~rmessing\/uradl\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0123","series-title":"Proc. Int. Conf. on Comp. Vis.","article-title":"Activity recognition using the velocity histories of tracked keypoints","author":"Messing","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0124","unstructured":"K. Yun, J. Honorio, D. Chattopadhyay, T.L. Berg, D. Samaras, Two-person interaction detection using body-pose features and multiple instance learning. Available at: http:\/\/www3.cs.stonybrook.edu\/~kyun\/research\/kinectinteraction\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0125","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops","article-title":"Two-person interaction detection using body-pose features and multiple instance learning","author":"Yun","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0126","unstructured":"B. Yao, X. Jiang, A. Khosla, A.L. Lin, L.J. Guibas, L. Fei-Fei, Stanford 40 Actions dataset. Available at: http:\/\/vision.stanford.edu\/Datasets\/40actions.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0127","series-title":"Proceedings of International Conference on Computer Vision","first-page":"1331","article-title":"Human action recognition by learning bases of action attributes and parts","author":"Yao","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0128","unstructured":"M. Tenorth, J. Bandouch, M. Beetz, TUM Kitchen dataset. Available at: https:\/\/ias.cs.tum.edu\/software\/kitchen-activity-data (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0129","series-title":"Proc. Int. Conf. on Comp. Vis. Workshops","first-page":"1089","article-title":"The TUM Kitchen Data Set of everyday manipulation activities for motion tracking and action recognition","author":"Tenorth","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0130","unstructured":"K. Soomro, A.R. Zamir, M. Shah, UCF101 action recognition dataset. Available at: http:\/\/crcv.ucf.edu\/data\/UCF101.php (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0131","series-title":"Technical report","article-title":"CRCV-TR-12-01: UCF101: a dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0132","unstructured":"J. Liu, J. Luo, M. Shah, UCF YouTube action dataset. Available at: http:\/\/crcv.ucf.edu\/data\/UCF YouTube Action.php (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0133","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1996","article-title":"Recognizing realistic actions from videos in the wild","author":"Liu","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0134","unstructured":"K.K. Reddy, M. Shah, UCF50 action recognition dataset. Available at: http:\/\/crcv.ucf.edu\/data\/UCF50.php (accessed 29.07.15)."},{"issue":"5","key":"10.1016\/j.cviu.2015.10.010_bib0135","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","article-title":"Recognizing 50 human action categories of web videos","volume":"24","author":"Reddy","year":"2012","journal-title":"Mach. Vis. Appl."},{"key":"10.1016\/j.cviu.2015.10.010_bib0136","unstructured":"M.D. Rodriguez, J. Ahmed, M. Shah, UCF Sports action dataset. Available at: http:\/\/crcv.ucf.edu\/data\/UCF Sports Action.php (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0137","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1","article-title":"Action MACH a spatio-temporal maximum average correlation height filter for action recognition","author":"Rodriguez","year":"2008"},{"key":"10.1016\/j.cviu.2015.10.010_bib0138","unstructured":"N. van der Aa, X. Luo, G. Giezeman, R. Tan, R. Veltkamp, Utrecht multi-person motion benchmark. Available at: http:\/\/www.projects.science.uu.nl\/umpm\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0139","series-title":"Proceedings of Workshop on Human Interaction in Computer Vision","article-title":"Utrecht multi-person motion benchmark: a multi-person dataset with synchronized video and motion capture data for evaluation of articulated human motion and interaction","author":"vander Aa","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0140","unstructured":"M.S. Ryoo, J.K. Aggarwal, UT-Interaction Dataset, ICPR contest on semantic description of human activities, 2010. http:\/\/cvrc.ece.utexas.edu\/SDHA2010\/Human_Interaction.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0141","series-title":"Proceedings of International Conference on Computer Vision","first-page":"1593","article-title":"Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities","author":"Ryoo","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0142","unstructured":"H. Ragheb, S. Velastin, P. Remagnino, T. Ellis, ViHASi: Virtual Human Action Silhouette data for the evaluation of silhouette-based action recognition methods. Available at: http:\/\/dipersec.king.ac.uk\/VIHASI\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0143","series-title":"Proceedings of International Conference on Distributed Smart Cameras","first-page":"1","article-title":"ViHASi: Virtual Human Action Silhouette data for the performance evaluation of silhouette-based action recognition methods","author":"Ragheb","year":"2008"},{"key":"10.1016\/j.cviu.2015.10.010_bib0144","unstructured":"S. Oh, A. Hoogs, A. Perera, N. Cuntoor, C.-C. Chen, J.T. Lee, S. Mukherjee, J. Aggarwal, H. Lee, L. Davis, E. Swears, X. Wang, Q. Ji, K. Reddy, M. Shah, C. Vondrick, H. Pirsiavash, D. Ramanan, J. Yuen, A. Torralba, B. Song, A. Fong, A. Roy-Chowdhury, M. Desai, VIRAT video dataset. Available at: http:\/\/www.viratdata.org\/ (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0145","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"A large-scale benchmark dataset for event recognition in surveillance video","volume":"vol. 2","author":"Oh","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0146","unstructured":"M. Blank, L. Gorelick, E. Shechtman, M. Irani, R. Basri, Actions as space-time shapes. Available at: http:\/\/www.wisdom.weizmann.ac.il\/~vision\/SpaceTimeActions.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0147","series-title":"Proceedings of International Conference on Computer Vision","first-page":"1395","article-title":"Actions as space-time shapes","author":"Blank","year":"2005"},{"key":"10.1016\/j.cviu.2015.10.010_bib0148","unstructured":"V. Kulathumani, WVU Multi-View action recognition dataset. Available at: http:\/\/csee.wvu.edu\/~vkkulathumani\/wvu-action.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0149","series-title":"Proceedings of International Conference on Distributed Smart Cameras","first-page":"1","article-title":"Real-time multi-view human action recognition using a wireless camera network","author":"Ramagiri","year":"2011"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0150","doi-asserted-by":"crossref","first-page":"486","DOI":"10.3390\/jsan2030486","article-title":"Real-time recognition of action sequences using a distributed video sensor network","volume":"2","author":"Kavi","year":"2013","journal-title":"J. Sens. Actuator Netw."},{"key":"10.1016\/j.cviu.2015.10.010_bib0151","series-title":"Proceedings of IEEE International Symposium on Robot and Human Interactive Communication","first-page":"509","article-title":"Audio-based human activity recognition using non-markovian ensemble voting","author":"Stork","year":"2012"},{"issue":"1","key":"10.1016\/j.cviu.2015.10.010_bib0152","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/TITB.2007.899496","article-title":"Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions","volume":"12","author":"Ermes","year":"2008","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"10.1016\/j.cviu.2015.10.010_bib0153","series-title":"Proceedings of International Conference on Pervasive and Embedded Computing and Communication Systems","article-title":"Macro-class selection for hierarchical K-NN classification of inertial sensor data","author":"McCall","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0154","series-title":"Proceedings of International Conference on Performance Evaluation of Tracking and Surveillance","article-title":"PETS","author":"Ferryman","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0155","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"A database for fine grained activity detection of cooking activities","volume":"vol. 6","author":"Rohrbach","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0156","series-title":"Proceedings of International Conference on Computer Vision","article-title":"Activity recognition using the velocity histories of tracked keypoints","author":"Messing","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0157","series-title":"Proceedings of International Conference on Computer Vision","first-page":"415","article-title":"Efficient regression of general-activity human poses from depth images","author":"Girshick","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0158","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1784","article-title":"Exemplar-based human action pose correction and tagging","author":"Shen","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0159","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"103","article-title":"The Vitruvian manifold : inferring dense correspondences for one-shot human pose estimation","author":"Taylor","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0160","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR\u201912","first-page":"1226","article-title":"Social interactions: a first-person perspective","author":"Fathi","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0161","series-title":"Proceedings of ACM\/IEEE International Conference on Human-Robot Interaction","first-page":"295","article-title":"Robot-centric activity prediction from first-person videos: what will they do to me?","author":"Ryoo","year":"2015"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0162","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1016\/j.eswa.2013.08.009","article-title":"Evolutionary joint selection to improve human action recognition with RGB-D devices","volume":"41","author":"Chaaraoui","year":"2014","journal-title":"Expert Syst. Appl."},{"issue":"4","key":"10.1016\/j.cviu.2015.10.010_bib0163","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1109\/TPAMI.2012.175","article-title":"Explicit modeling of human\u2013object interactions in realistic videos","volume":"35","author":"Prest","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10.1016\/j.cviu.2015.10.010_bib0164","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1109\/TPAMI.2010.156","article-title":"Action recognition from one example","volume":"33","author":"Seo","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"10.1016\/j.cviu.2015.10.010_bib0165","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1007\/s00138-012-0449-x","article-title":"Classifying web videos using a global video descriptor","volume":"24","author":"Solmaz","year":"2012","journal-title":"Mach. Vis. Appl."},{"key":"10.1016\/j.cviu.2015.10.010_bib0166","series-title":"Proceedings of European Conference on Computer Vision","first-page":"256","article-title":"Motion interchange patterns for action recognition in unconstrained videos","author":"Kliper-gross","year":"2012"},{"issue":"11","key":"10.1016\/j.cviu.2015.10.010_bib0167","doi-asserted-by":"crossref","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","article-title":"Temporal localization of actions with actoms","volume":"35","author":"Gaidon","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0168","series-title":"Proceedings of International Conference on Computer Vision","first-page":"1","article-title":"Action recognition from arbitrary views using 3D exemplars","author":"Weinland","year":"2007"},{"key":"10.1016\/j.cviu.2015.10.010_bib0169","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"489","article-title":"Action recognition using context and appearance distribution features","author":"Wu","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0170","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1362","article-title":"Cross-view activity recognition using Hankelets","author":"Li","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0171","series-title":"Proceedings of International Conference on Computer Vision","first-page":"3176","article-title":"Learning view-invariant sparse representations for cross-view action recognition","author":"Zheng","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0172","series-title":"Proceedings of International Conference on Pattern Recognition","first-page":"52","article-title":"Velocity adaptation of space-time interest points","volume":"vol. 1","author":"Laptev","year":"2004"},{"key":"10.1016\/j.cviu.2015.10.010_bib0173","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1948","article-title":"Recognising action as clouds of space-time interest points","author":"Bregonzio","year":"2009"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0174","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/TPAMI.2011.147","article-title":"Recognizing human actions by learning and matching shape-motion prototype trees","volume":"34","author":"Jiang","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0175","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1109\/TCSVT.2013.2276856","article-title":"Detecting human action as the spatio-temporal tube of maximum mutual information","volume":"24","author":"Wang","year":"2014","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0176","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.cviu.2011.09.010","article-title":"Selective spatio-temporal interest points","volume":"116","author":"Chakraborty","year":"2012","journal-title":"Comp. Vis. Image Underst."},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0177","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1109\/TPAMI.2012.141","article-title":"Action spotting and recognition based on a spatiotemporal orientation analysis","volume":"35","author":"Derpanis","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0178","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1109\/TMM.2011.2128301","article-title":"Fast action detection via discriminative random forest voting and top-K subvolume search","volume":"13","author":"Yu","year":"2011","journal-title":"IEEE Trans. Multimed."},{"issue":"11","key":"10.1016\/j.cviu.2015.10.010_bib0179","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1016\/j.imavis.2013.08.005","article-title":"Human activity recognition in videos using a single example","volume":"31","author":"Javan Roshtkhari","year":"2013","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.cviu.2015.10.010_bib0180","unstructured":"Stanford Vision Lab, Stanford 40 Actions: a dataset for understanding human actions in still images. Available at: http:\/\/vision.stanford.edu\/Datasets\/40actions.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0181","series-title":"Proceedings of European Conference on Computer Vision","first-page":"263","article-title":"On recognizing actions in still images via multiple features","author":"Sener","year":"2012"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0182","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/s11263-013-0633-0","article-title":"Coloring action recognition in still images","volume":"105","author":"Khan","year":"2013","journal-title":"Int. J. Comp. Vis."},{"key":"10.1016\/j.cviu.2015.10.010_bib0183","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1725","article-title":"Large-scale video classification with convolutional neural networks","author":"Karpathy","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0184","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1234","article-title":"Action bank: a high-level representation of activity in video","author":"Sadanand","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0185","series-title":"Proceedings of IEEE Workshop on Applications of Computer Vision","first-page":"103","article-title":"Spatio-temporal covariance descriptors for action and gesture recognition","author":"Sanin","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0186","series-title":"Proceedings of International Conference on Pattern Recognition","first-page":"979","article-title":"RBM-based Silhouette encoding for human action modelling","volume":"vol. 1","author":"Marin-Jim\u00e9nez","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0187","series-title":"IEEE International Conference on Advanced Video and Signal Based Surveillance","first-page":"43","article-title":"Recognizing human actions using Silhouette-based HMM","author":"Mart\u00ednez-Contreras","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0188","series-title":"Proceedings of International Conference on Computer Vision Workshops","first-page":"1318","article-title":"Human action silhouette recognition based on tensor analysis using synthetic silhouette data","author":"Lee","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0189","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"25","article-title":"A unified framework for locating and recognizing human actions","author":"Xie","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0190","series-title":"Proceedings of IEEE Conference on Electrical and Electronics Engineering","first-page":"315","article-title":"Action recognition using random forest prediction with combined pose-based and motion-based features","author":"Ar","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0191","series-title":"Proceedings of International Conference on Computer Vision","first-page":"1419","article-title":"Action recognition in videos acquired by a moving camera using motion decomposition of Lagrangian particle trajectories","author":"Wu","year":"2011"},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0192","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/TSMCB.2011.2166761","article-title":"Cross-domain human action recognition","volume":"42","author":"Bian","year":"2012","journal-title":"IEEE Trans. Syst. Man Cybern. Part B: Cybern."},{"issue":"7","key":"10.1016\/j.cviu.2015.10.010_bib0193","doi-asserted-by":"crossref","first-page":"8750","DOI":"10.3390\/s130708750","article-title":"Multi-view human activity recognition in distributed camera sensor networks","volume":"13","author":"Mosabbeb","year":"2013","journal-title":"Sensors"},{"key":"10.1016\/j.cviu.2015.10.010_bib0194","unstructured":"S.J. Blunsden, R.B. Fisher, BEHAVE Optical Flow Data. Available at: http:\/\/groups.inf.ed.ac.uk\/vision\/BEHAVEDATA\/CROWDS\/index.html (accessed 29.07.15)."},{"key":"10.1016\/j.cviu.2015.10.010_bib0195","series-title":"Proceedings of International Conference on Pattern Recognition","first-page":"175","article-title":"Modelling crowd scenes for event detection","author":"Andrade","year":"2006"},{"key":"10.1016\/j.cviu.2015.10.010_bib0196","series-title":"Proceedings of IEEE Symposium on Imaging for Crime Detection and Prevention","first-page":"528","article-title":"Detection of emergency events in crowded scenes","author":"Andrade","year":"2006"},{"key":"10.1016\/j.cviu.2015.10.010_bib0197","series-title":"IEEE International Conference on Image Processing","first-page":"2709","article-title":"Small group human activity recognition","author":"Yin","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0198","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1007\/978-3-642-33161-9_76","article-title":"Towards a real-time situational awareness system for surveillance applications in unconstrained environments","volume":"318","author":"M\u00fcnch","year":"2012","journal-title":"Future Secur."},{"key":"10.1016\/j.cviu.2015.10.010_bib0199","series-title":"Proceedings of International Conference on Computer and Robot Vision","first-page":"268","article-title":"Real-time semantics-based detection of suspicious activities in public spaces","author":"Elhamod","year":"2012"},{"issue":"2","key":"10.1016\/j.cviu.2015.10.010_bib0200","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1109\/TITS.2012.2228640","article-title":"Automated real-time detection of potentially suspicious behavior in public transport areas","volume":"14","author":"Elhamod","year":"2013","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0201","series-title":"Proceedings of International Workshop on Human Activity Record and Modelling","article-title":"Segmentation and classification of human activities","author":"Nascimento","year":"2005"},{"key":"10.1016\/j.cviu.2015.10.010_bib0202","series-title":"Proceedings of IEEE International Conference on Image Processing","article-title":"Recognition of human activities using space dependent switched dynamical models","author":"Nascimento","year":"2005"},{"key":"10.1016\/j.cviu.2015.10.010_bib0203","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1007\/978-3-642-14061-7_8","article-title":"A proposal for local and global human activities identification","volume":"6169","author":"Fern\u00e1ndez-Caballero","year":"2010","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.cviu.2015.10.010_bib0204","series-title":"International Conference on Signal Processing and Communication Systems","first-page":"1","article-title":"Object tracking using multiple motion modalities","author":"Denman","year":"2008"},{"key":"10.1016\/j.cviu.2015.10.010_bib0205","series-title":"Visual Analysis of Humans","first-page":"109","article-title":"Benchmark datasets for detection and tracking","author":"Ellis","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0206","series-title":"Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance","first-page":"377","article-title":"Activity recognition and uncertain knowledge in video scenes","author":"Romdhane","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0207","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"526","article-title":"Action and interaction recognition in first- person videos","author":"Narayan","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0208","series-title":"Proc. IEEE Conf. on Comp. Vis. and Pat. Rec. Workshops","first-page":"535","article-title":"Understanding the nature of first-person videos: characterization and classification using low-level features","author":"Tan","year":"2014"},{"issue":"5","key":"10.1016\/j.cviu.2015.10.010_bib0209","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1109\/TCSVT.2015.2409731","article-title":"An overview of first person vision and egocentric video analysis for personal mobile wearable devices","volume":"25","author":"Betancourt","year":"2014","journal-title":"Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2015.10.010_bib0210","series-title":"Proceedings of International Conference on Computer Vision","first-page":"1036","article-title":"Human activity prediction: early recognition of ongoing activities from streaming videos","author":"Ryoo","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0211","series-title":"Proceedings of International Conference on Computer Vision","first-page":"778","article-title":"Learning spatiotemporal graphs of human activities","author":"Brendel","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0212","series-title":"Proceedings of Indian Conference on Computer Vision, Graphics and Image Processing","first-page":"31:1","article-title":"The role of spatial context in activity recognition","author":"Zhu","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0213","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2561","article-title":"A hierarchical context model for event recognition in surveillance video","author":"Wang","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0214","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.cviu.2015.02.012","article-title":"Discriminative key-component models for interaction detection and recognition","volume":"135","author":"Sefidgar","year":"2015","journal-title":"Comp. Vis. Image Underst."},{"issue":"7","key":"10.1016\/j.cviu.2015.10.010_bib0215","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1109\/TIP.2015.2404034","article-title":"Hierarchical graphical models for simultaneous tracking and recognition in wide-area scenes","volume":"24","author":"Nayak","year":"2015","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"10.1016\/j.cviu.2015.10.010_bib0216","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1109\/TCSVT.2009.2029024","article-title":"Human behavior analysis based on a new motion descriptor","volume":"19","author":"Huang","year":"2009","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2015.10.010_bib0217","series-title":"Proceedings of International Conference on Image Processing","first-page":"1121","article-title":"A compact optical flow based motion representation for real-time action recognition in surveillance scenes","author":"Wang","year":"2009"},{"issue":"4","key":"10.1016\/j.cviu.2015.10.010_bib0218","doi-asserted-by":"crossref","first-page":"2187","DOI":"10.1109\/TIP.2011.2176346","article-title":"A discriminative model of motion and cross ratio for view-invariant action recognition","volume":"21","author":"Huang","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2015.10.010_bib0219","series-title":"Proceedings of European Conference on Computer Vision","first-page":"577","article-title":"Tracklet descriptors for action modeling and video analysis","volume":"6311","author":"Raptis","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0220","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Action recognition by dense trajectories","author":"Wang","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0221","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"536","article-title":"Modeling the temporal extent of actions","author":"Satkin","year":"2010"},{"key":"10.1016\/j.cviu.2015.10.010_bib0222","series-title":"Proceedings of European Conference on Computer Vision","first-page":"508","article-title":"Representing pairwise spatial and temporal relations for action recognition","author":"Matikainen","year":"2010"},{"issue":"1","key":"10.1016\/j.cviu.2015.10.010_bib0223","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/THMS.2014.2362520","article-title":"Improving human action recognition using fusion of depth camera and inertial sensors","volume":"45","author":"Chen","year":"2015","journal-title":"IEEE Trans. Human-Mach. Syst."},{"key":"10.1016\/j.cviu.2015.10.010_bib0224","doi-asserted-by":"crossref","unstructured":"S. Vantigodi, R. Babu, Real-time human action recognition from motion capture data, in: Proceedings of National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, 2013, pp. 1\u20134.","DOI":"10.1109\/NCVPRIPG.2013.6776204"},{"key":"10.1016\/j.cviu.2015.10.010_bib0225","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.patrec.2013.09.024","article-title":"Human activity recognition by separating style and content","volume":"50","author":"Cheema","year":"2014","journal-title":"Pattern Recognition Letters"},{"issue":"1","key":"10.1016\/j.cviu.2015.10.010_bib0226","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.jvcir.2013.04.007","article-title":"Sequence of the most informative joints (SMIJ): a new representation for human skeletal action recognition","volume":"25","author":"Ofli","year":"2014","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"5","key":"10.1016\/j.cviu.2015.10.010_bib0227","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1109\/TPAMI.2008.80","article-title":"Distribution-based dimensionality reduction applied to articulated motion recognition","volume":"31","author":"Nayak","year":"2009","journal-title":"IEEE Trans. Pattern. Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0228","series-title":"Proceedings of European Signal Processing Conference","first-page":"1317","article-title":"Human action recognition in stereoscopic videos based on bag of features and disparity pyramids","author":"Iosifidis","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0229","series-title":"Proceedings of Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing","first-page":"1","article-title":"Stereoscopic video description for human action recognition","author":"Mademlis","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0230","series-title":"Proceedings of European Conference on Computer Vision","first-page":"758","article-title":"Natural action recognition using invariant 3d motion encoding","volume":"vol. 8690","author":"Hadfield","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0231","series-title":"Technical report","article-title":"Humaneva: synchronized video and motion capture dataset for evaluation of articulated human motion","author":"Sigal","year":"2006"},{"key":"10.1016\/j.cviu.2015.10.010_bib0232","series-title":"Proceedings of ACM\/IEEE International Conference on Distributed Smart Cameras","first-page":"1","article-title":"View-invariant 3d human body pose reconstruction using a monocular video camera","author":"Ke","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0233","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Tracking 3d human pose with large root node uncertainty","author":"Daubney","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0234","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"14","article-title":"Eigenjoints-based action recognition using naive-Bayes-nearest-neighbor","author":"Yang","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0235","series-title":"Proceedings of European Conference on Computer Vision","first-page":"872","article-title":"Robust 3d action recognition with random occupancy patterns","author":"Wang","year":"2012"},{"key":"10.1016\/j.cviu.2015.10.010_bib0236","series-title":"Proceedings of International Conference on Pattern Recognition","first-page":"3499","article-title":"Grassmannian representation of motion depth for 3D human gesture and action recognition","author":"Slama","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0237","series-title":"Proceedings of IEEE-RAS International Conference on Humanoid Robots","first-page":"987","article-title":"Manipulation action tree bank: a knowledge resource for humanoids","author":"Yang","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0238","series-title":"Proceedings of International Workshop on Multimedia for Cooking and Eating Activities","first-page":"39","article-title":"User-adaptive models for recognizing food preparation activities","author":"Stein","year":"2013"},{"key":"10.1016\/j.cviu.2015.10.010_bib0239","series-title":"Proceedings of International Conference on Computer Vision Workshops","first-page":"1264","article-title":"UMPM benchmark: a multi-person dataset with synchronized video and motion capture data for evaluation of articulated human motion and interaction","author":"van der Aa","year":"2011"},{"key":"10.1016\/j.cviu.2015.10.010_bib0240","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"17","article-title":"Temporal segmentation and activity classification from first-person sensing","author":"Spriggs","year":"2009"},{"issue":"12","key":"10.1016\/j.cviu.2015.10.010_bib0241","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1109\/LSP.2013.2284196","article-title":"Joint action segmentation and classification by an extended hidden Markov model","volume":"20","author":"Borzeshi","year":"2013","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.cviu.2015.10.010_bib0242","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"479","article-title":"Recognizing actions from depth cameras as weakly aligned multi-part bag-of-poses","author":"Seidenari","year":"2013"},{"issue":"6","key":"10.1016\/j.cviu.2015.10.010_bib0243","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1109\/TCYB.2014.2347057","article-title":"Multipe\/single-view human action recognition via part-induced multitask structural learning","volume":"45","author":"Liu","year":"2015","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.cviu.2015.10.010_bib0244","series-title":"Proceedings of IEEE-RAS International Conference on Humanoid Robots","first-page":"112","article-title":"Learning basis skills by autonomous segmentation of humanoid motion trajectories","author":"Lee","year":"2012"},{"issue":"6","key":"10.1016\/j.cviu.2015.10.010_bib0245","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1109\/TPAMI.2013.245","article-title":"On-line video event detection by constraint flow","volume":"36","author":"Kwak","year":"2014","journal-title":"IEEE Trans. Pattern Anal Mach. Intell."},{"key":"10.1016\/j.cviu.2015.10.010_bib0246","series-title":"Proceedings of International Conference on Computer Vision","article-title":"Action detection in complex scenes with spatial and temporal ambiguities","author":"Hu","year":"2009"},{"key":"10.1016\/j.cviu.2015.10.010_bib0247","series-title":"Proceedings of International Conference on Multimedia","first-page":"357","article-title":"A 3-dimensional sift descriptor and its application to action recognition","author":"Scovanner","year":"2007"},{"issue":"2\u20133","key":"10.1016\/j.cviu.2015.10.010_bib0248","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","article-title":"On space-time interest points","volume":"64","author":"Laptev","year":"2005","journal-title":"Int. J. Comp. Vis."},{"key":"10.1016\/j.cviu.2015.10.010_bib0249","series-title":"Proceedings of International Conference on Image Analysis and Rec.","article-title":"Conversational interaction recognition based on bodily and facial movement","author":"Deng","year":"2014"},{"key":"10.1016\/j.cviu.2015.10.010_bib0250","series-title":"Proceedings of ARPA Human Language Technology Workshops","first-page":"119","article-title":"Topic and speaker identification via large vocabulary continuous speaker recognition","author":"Peskin","year":"1993"},{"issue":"3","key":"10.1016\/j.cviu.2015.10.010_bib0251","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1093\/ietisy\/e88-d.3.446","article-title":"Dialogue speech recognition by combining hierarchical topic classification and language model switching","volume":"88","author":"Lane","year":"2005","journal-title":"IEICE Trans. Inf. Syst."},{"issue":"9","key":"10.1016\/j.cviu.2015.10.010_bib0252","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1016\/j.specom.2006.04.003","article-title":"Emotional speech recognition: resources, features, and methods","volume":"48","author":"Ververidis","year":"2006","journal-title":"Speech Commun."},{"key":"10.1016\/j.cviu.2015.10.010_bib0253","series-title":"Proceedings of International Joint Conference on Neural Networks","first-page":"1","article-title":"SVM with entropy regularization and particle swarm optimization for identifying children\u2019s health and socioeconomic determinants of education attainments using linked datasets","author":"Zhou","year":"2010"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314215002209?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314215002209?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T20:57:29Z","timestamp":1536872249000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314215002209"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":253,"alternative-id":["S1077314215002209"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2015.10.010","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2016,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From pose to activity: Surveying datasets and introducing CONVERSE","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2015.10.010","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Copyright \u00a9 2015 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}