{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:03:21Z","timestamp":1760346201920,"version":"3.38.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2011,3,1]],"date-time":"2011-03-01T00:00:00Z","timestamp":1298937600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2011,3]]},"DOI":"10.1007\/s12559-011-9097-0","type":"journal-article","created":{"date-parts":[[2011,3,10]],"date-time":"2011-03-10T16:58:50Z","timestamp":1299776330000},"page":"167-184","source":"Crossref","is-referenced-by-count":11,"title":["Spatiotemporal Features for Action Recognition and Salient Event Detection"],"prefix":"10.1007","volume":"3","author":[{"given":"Konstantinos","family":"Rapantzikos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannis","family":"Avrithis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanos","family":"Kollias","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,3,11]]},"reference":[{"key":"9097_CR1","doi-asserted-by":"crossref","unstructured":"James W. The principles of psychology; 1890.","DOI":"10.1037\/10538-000"},{"issue":"1","key":"9097_CR2","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"A Treisman","year":"1980","unstructured":"Treisman A. A feature-integration theory of attention. Cogn Psychol. 1980;12(1):97\u2013136.","journal-title":"Cogn Psychol"},{"key":"9097_CR3","first-page":"219","volume":"4","author":"C Koch","year":"1985","unstructured":"Koch C. Shifts in selective visual attention: towards the underlying neural circuitry. Comput Vis Image Underst 1985;4:219\u201327.","journal-title":"Computer Vision and Image Understanding"},{"issue":"11","key":"9097_CR4","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti L, Koch C. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 1998;20(11):1254\u201359 doi: 10.1109\/34.730558 .","journal-title":"Pattern Analysis and Machine Intelligence, IEEE Transactions on"},{"issue":"8","key":"9097_CR5","doi-asserted-by":"crossref","first-page":"2428","DOI":"10.1117\/12.205668","volume":"34","author":"R Milanese","year":"1995","unstructured":"Milanese R, Gil S. Attentive mechanisms for dynamic and static scene analysis. Opt Eng 1995;34(8):2428\u201334.","journal-title":"Optical Engineering"},{"key":"9097_CR6","doi-asserted-by":"crossref","unstructured":"Rapantzikos K, Tsapatsoulis N. Spatiotemporal visual attention architecture for video analysis. In: Multimedia signal processing, 2004 IEEE 6th workshop on 2004. p. 83\u20136.","DOI":"10.1109\/MMSP.2004.1436423"},{"key":"9097_CR7","unstructured":"Rapantzikos K. Coupled hidden markov models for complex action recognition. In: An enhanced spatiotemporal visual attention model for sports video analysis, international workshop on content-based multimedia indexing (CBMI); 2005."},{"issue":"2","key":"9097_CR8","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1049\/iet-ipr:20060040","volume":"1","author":"K Rapantzikos","year":"2007","unstructured":"Rapantzikos K, Tsapatsoulis N. A bottom-up spatiotemporal visual attention model for video analysis. IET Image Process. 2007;1(2):237\u201348.","journal-title":"IET Image Processing"},{"key":"9097_CR9","doi-asserted-by":"crossref","unstructured":"Rapantzikos K, Avrithis Y. Dense saliency-based spatiotemporal feature points for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE; 2009.","DOI":"10.1109\/CVPRW.2009.5206525"},{"key":"9097_CR10","volume-title":"Principles of Gestalt Psychology","author":"K Koffka","year":"1935","unstructured":"Koffka K. Principles of Gestalt psychology. New York: Harcourt; 1935."},{"key":"9097_CR11","doi-asserted-by":"crossref","unstructured":"Wertheimer M. Laws of organization in perceptual forms (partial translation). A sourcebook of Gestalt psychology; 1938.","DOI":"10.1037\/11496-005"},{"issue":"9","key":"9097_CR12","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1016\/0042-6989(94)90300-X","volume":"34","author":"J Wolfe","year":"1994","unstructured":"Wolfe J. Visual search in continuous, naturalistic stimuli. Vis Res(Oxf). 1994;34(9):1187\u201395.","journal-title":"Vision research(Oxford)"},{"issue":"1-2","key":"9097_CR13","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/0004-3702(95)00025-9","volume":"78","author":"JK Tsotsos","year":"1995","unstructured":"Tsotsos JK, Culhane SM. Modeling visual attention via selective tuning. Artif Intell. 1995;78(1\u20132):507\u201345.","journal-title":"Artif Intell Eng Des Anal Manuf"},{"key":"9097_CR14","doi-asserted-by":"crossref","unstructured":"Harris C. A combined corner and edge detector. In: Alvey vision conference 1988. vol 15, p. 50.","DOI":"10.5244\/C.2.23"},{"issue":"2","key":"9097_CR15","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1008045108935","volume":"30","author":"T Lindeberg","year":"1998","unstructured":"Lindeberg T. Feature detection with automatic scale selection. Int J Comput Vis. 1998;30(2):79\u2013116.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"9097_CR16","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1023\/A:1012460413855","volume":"45","author":"T Kadir","year":"2001","unstructured":"Kadir T. Saliency, scale and image description. Int J Comput Vis 2001;45(2):83\u2013105.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"9097_CR17","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s11263-005-3848-x","volume":"65","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk K, Tuytelaars T. A comparison of affine region detectors. Int J Comput Vis 2005;65(1):43\u201372.","journal-title":"International Journal of Computer Vision"},{"key":"9097_CR18","unstructured":"Csurka G, Dance C. Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, ECCV; 2004. p. 1\u201322."},{"key":"9097_CR19","doi-asserted-by":"crossref","unstructured":"Mikolajczyk K. An affine invariant interest point detector. Lect Notes Comput Sci. 2002;128\u2013142.","DOI":"10.1007\/3-540-47969-4_9"},{"key":"9097_CR20","unstructured":"Koch C. Visual categorization with bags of key-points. In: European conference on computer vision; 2004. p. 1\u201322."},{"key":"9097_CR21","unstructured":"Hao YW. Unsupervised discovery of action classes. Comput Vis Pattern Recognit. 2006;2:17\u201322"},{"key":"9097_CR22","doi-asserted-by":"crossref","unstructured":"Bosch A, Zisserman A. Scene classification via plsa. In: European conference on computer vision; 2006. p. 517\u201330.","DOI":"10.1007\/11744085_40"},{"key":"9097_CR23","doi-asserted-by":"crossref","unstructured":"Laptev I. Interest point detection and scale selection in space-time. Lect Notes Comput Sci. 2003;372\u2013387.","DOI":"10.1007\/3-540-44935-3_26"},{"issue":"2","key":"9097_CR24","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev I. On space-time interest points. Int J Comput Vis. 2005;64(2):107\u201323.","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"9097_CR25","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.cviu.2006.11.023","volume":"108","author":"I Laptev","year":"2007","unstructured":"Laptev I, Caputo B. Local velocity-adapted motion events for spatio-temporal recognition. Comput Vis Image Underst. 2007;108(3):207\u201329.","journal-title":"Computer Vision and Image Understanding"},{"key":"9097_CR26","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r P, Rabaud V. Behavior recognition via sparse spatio-temporal features. In: 2nd Joint IEEE International Workshop on visual surveillance and performance evaluation of tracking and surveillance, 2005; 2005. p. 65\u201372.","DOI":"10.1109\/VSPETS.2005.1570899"},{"issue":"3","key":"9097_CR27","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles JC, Wang H. Unsupervised learning of human action categories using spatial-temporal words. Int J Comput Vis. 2008;79(3):299\u2013318.","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"9097_CR28","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1109\/TSMCB.2005.861864","volume":"36","author":"A Oikonomopoulos","year":"2006","unstructured":"Oikonomopoulos A, Patras I. Spatiotemporal salient points for visual recognition of human actions. IEEE Trans Syst Man Cybern B Cybern. 2006;36(3):710\u20139.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics"},{"key":"9097_CR29","doi-asserted-by":"crossref","unstructured":"Wong SF. Extracting spatiotemporal interest points using global information. In: IEEE 11th International Conference on Computer Vision, 2007. ICCV 2007; 2007. p. 1\u20138.","DOI":"10.1109\/ICCV.2007.4408923"},{"key":"9097_CR30","doi-asserted-by":"crossref","unstructured":"Blank M, Gorelick L. Actions as space-time shapes. In: Tenth IEEE International Conference on Computer Vision, 2005. ICCV 2005; 2005. p. 2.","DOI":"10.1109\/ICCV.2005.28"},{"key":"9097_CR31","doi-asserted-by":"crossref","unstructured":"Shechtman E. Space-time behavior based correlation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005; 2005. p. 1.","DOI":"10.1109\/CVPR.2005.328"},{"key":"9097_CR32","doi-asserted-by":"crossref","unstructured":"Shechtman E. Matching local self-similarities across images and videos. In: Proceedings of CVPR; 2007.","DOI":"10.1109\/CVPR.2007.383198"},{"key":"9097_CR33","unstructured":"Ke Y. PCA-SIFT: a more distinctive representation for local image descriptors. In: IEEE Compuer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 1999; 2004. p. 2."},{"key":"9097_CR34","unstructured":"Hamid R, Johnson A. Detection and explanation of anomalous activities: representing activities as bags of event n-Grams. In: IEEE Compuer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 1999; 2005. vol 1, p. 1031."},{"key":"9097_CR35","doi-asserted-by":"crossref","unstructured":"Itti L. A principled approach to detecting surprising events in video. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR05); 2005. p. 1.","DOI":"10.1109\/CVPR.2005.40"},{"key":"9097_CR36","unstructured":"Zhong H, Shi J. Detecting unusual activity in video. In: IEEE Compuer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society 1999; 2004. p. 2."},{"key":"9097_CR37","doi-asserted-by":"crossref","unstructured":"Ma YF, Lu L. A user attention model for video summarization. In: Proceedings of the tenth ACM international conference on Multimedia. New York: ACM; 2002. p. 533\u201342.","DOI":"10.1145\/641113.641116"},{"issue":"5","key":"9097_CR38","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1109\/TMM.2005.854410","volume":"7","author":"YF Ma","year":"2005","unstructured":"Ma YF, Hua XS. A generic framework of user attention model and its application in video summarization. IEEE Trans Multimed. 2005;7(5):907\u201319.","journal-title":"Multimedia. IEEE Transactions on"},{"key":"9097_CR39","doi-asserted-by":"crossref","unstructured":"Boiman O. Detecting irregularities in images and in video. In: IEEE International Conference on Computer Vision (ICCV); 2005.","DOI":"10.1109\/ICCV.2005.70"},{"issue":"8","key":"9097_CR40","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1109\/34.868677","volume":"22","author":"C Stauffer","year":"2000","unstructured":"Stauffer C. Learning patterns of activity using real-time tracking. IEEE Trans Pattern Anal Mach Intell. 2000;22(8):747\u201357.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9097_CR41","doi-asserted-by":"crossref","unstructured":"Adam A, Rivlin E. Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans Pattern Anal Mach Intell. 2008; 555\u201360.","DOI":"10.1109\/TPAMI.2007.70825"},{"key":"9097_CR42","doi-asserted-by":"crossref","unstructured":"Evangelopoulos G, Rapantzikos K. Movie summarization based on audiovisual saliency detection. In: 15th IEEE International Conference on Image Processing, 2008. ICIP 2008; 2008. p. 2528\u201331.","DOI":"10.1109\/ICIP.2008.4712308"},{"key":"9097_CR43","doi-asserted-by":"crossref","unstructured":"Evangelopoulos G. Video event detection and summarization using audio, visual and text saliency. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP09); 2009. p. 3553\u20136.","DOI":"10.1109\/ICASSP.2009.4960393"},{"key":"9097_CR44","doi-asserted-by":"crossref","unstructured":"Rapantzikos K, Evangelopoulos G. An audio-visual saliency model for movie summarization. In: Proceedings of IEEE International Workshop on Multimedia Signal Processing (MMSP07); 2007.","DOI":"10.1109\/MMSP.2007.4412882"},{"key":"9097_CR45","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1109\/TPAMI.2002.1046148","volume":"24","author":"Y Caspi","year":"2002","unstructured":"Caspi Y. Spatio-temporal alignment of sequences. IEEE Trans Pattern Anal Mach Intell (PAMI). 2002;24:1409\u201324.","journal-title":"IEEE Trans on Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"9097_CR46","volume-title":"Solution of ill-posed problems","author":"AN Tikhonov","year":"1977","unstructured":"Tikhonov AN. Solution of ill-posed problems. Washington, DC: W. H. Winston; 1977."},{"key":"9097_CR47","doi-asserted-by":"crossref","unstructured":"Rapantzikos K. Robust optical flow estimation in MPEG sequences. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. (ICASSP\u201905); 2005. p. 2.","DOI":"10.1109\/ICASSP.2005.1415549"},{"key":"9097_CR48","volume-title":"Outlines of a Theory of the Light Sense","author":"E Hering","year":"1964","unstructured":"Hering E. Outlines of a theory of the light sense. Cambridge: Harvard University Press; 1964."},{"issue":"9","key":"9097_CR49","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1109\/34.93808","volume":"13","author":"WT Freeman","year":"1991","unstructured":"Freeman WT. The design and use of steerable filters. IEEE Trans Pattern Anal Mach Intell. 1991;13(9):891\u2013906.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9097_CR50","doi-asserted-by":"crossref","unstructured":"Derpanis KG. Three-dimensional nth derivative of gaussian separable steerable filters. In: IEEE International Conference on Image Processing; 2005.","DOI":"10.1109\/ICIP.2005.1530451"},{"key":"9097_CR51","doi-asserted-by":"crossref","unstructured":"Wildes R. Qualitative spatiotemporal analysis using an oriented energy representation. Lect Notes Comput Sci. 2000;768\u201384.","DOI":"10.1007\/3-540-45053-X_49"},{"key":"9097_CR52","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/0920-5489(94)90017-5","volume":"16","author":"M Riedmiller","year":"1994","unstructured":"Riedmiller M. Advanced supervised learning in multi-layer perceptrons\u2014from backpropagation to adaptive learning algorithms. Int J Comput Stand Interf Spec Issue Neural Netw. 1994;16:265\u201378.","journal-title":"Int Journal of Computer Standards and Interfaces, special Issue on Neural Networks"},{"key":"9097_CR53","unstructured":"Schuldt C, Laptev I. Recognizing human actions: a local SVM approach. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. 2004. p. 3."},{"key":"9097_CR54","doi-asserted-by":"crossref","unstructured":"Laptev I, Marszalek M. Learning realistic human actions from movies. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2008.","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"9097_CR55","doi-asserted-by":"crossref","unstructured":"Ke Y, Sukthankar R. Spatio-temporal shape and flow correlation for action recognition. In: 7th International Workshop on Visual Surveillance; 2007.","DOI":"10.1109\/CVPR.2007.383512"},{"key":"9097_CR56","doi-asserted-by":"crossref","unstructured":"Willems G, Tuytelaars T. An efficient dense and scale-invariant spatio-temporal interest point detector. In: Lecture Notes in Computer Science, Marseille, France; 2008. p. 650\u20133.","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"9097_CR57","unstructured":"Jiang H, Drew MS. Successive convex matching for action detection. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition; 2006. p. 1646\u201353."},{"key":"9097_CR58","unstructured":"Sivic J, Russell BC, Efros A, Zisserman A, Freeman WT. Discovering object categories in image collections. In: International Conference on Computer Vision (ICCV05); 2005."},{"issue":"1","key":"9097_CR59","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster AP, Laird NM. Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc 1977;39(1):1\u201338.","journal-title":"J R Stat Soc B"},{"key":"9097_CR60","unstructured":"MUSCLE. Movie dialogue dataBase v1. 1. Aristotle University of Thessaloniki, AIILab; 2007."}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-011-9097-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12559-011-9097-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-011-9097-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T01:32:25Z","timestamp":1741051945000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12559-011-9097-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,3]]},"references-count":60,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,3]]}},"alternative-id":["9097"],"URL":"https:\/\/doi.org\/10.1007\/s12559-011-9097-0","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"type":"print","value":"1866-9956"},{"type":"electronic","value":"1866-9964"}],"subject":[],"published":{"date-parts":[[2011,3]]}}}