{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T18:47:55Z","timestamp":1766515675790,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,12,7]],"date-time":"2017-12-07T00:00:00Z","timestamp":1512604800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Spain\u2019s Ministry of Economy and Competitiveness","award":["TIN2011-24367"],"award-info":[{"award-number":["TIN2011-24367"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1007\/s00138-017-0894-7","type":"journal-article","created":{"date-parts":[[2017,12,7]],"date-time":"2017-12-07T08:47:48Z","timestamp":1512636468000},"page":"207-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Spatio-temporal elastic cuboid trajectories for efficient fight recognition using Hough forests"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3869-9369","authenticated-orcid":false,"given":"Ismael","family":"Serrano","sequence":"first","affiliation":[]},{"given":"Oscar","family":"Deniz","sequence":"additional","affiliation":[]},{"given":"Gloria","family":"Bueno","sequence":"additional","affiliation":[]},{"given":"Guillermo","family":"Garcia-Hernando","sequence":"additional","affiliation":[]},{"given":"Tae-Kyun","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,7]]},"reference":[{"issue":"6","key":"894_CR1","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.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976\u2013990 (2010)","journal-title":"Image Vis. Comput."},{"issue":"11","key":"894_CR2","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1109\/TCSVT.2008.2005594","volume":"18","author":"P Turaga","year":"2008","unstructured":"Turaga, P., Chellappa, R., Subrahmanian, V., Udrea, O.: Machine recognition of human activities: a survey. Circuits Syst. Video Technol. IEEE Trans. 18(11), 1473\u20131488 (2008)","journal-title":"Circuits Syst. Video Technol. IEEE Trans."},{"issue":"2","key":"894_CR3","doi-asserted-by":"crossref","first-page":"88","DOI":"10.3390\/computers2020088","volume":"2","author":"K Shian-Ru","year":"2013","unstructured":"Shian-Ru, K., Hoang Le Uyen, T., Yong-Jin, L., Jenq-Neng, H., Jang-Hee, Y., et al.: A review on video-based human activity recognition. Computers 2(2), 88\u2013131 (2013)","journal-title":"Computers"},{"key":"894_CR4","doi-asserted-by":"crossref","unstructured":"Laptev, I., Lindeberg, T.: Space-time interest points. In: Proceedings of International Conference on Computer Vision, pp. 432\u2013439. (2003)","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"894_CR5","doi-asserted-by":"crossref","unstructured":"Bermejo, E., Deniz, O., Bueno, G., Sukthankar, R.: Violence detection in video using computer vision techniques. In: 14th International Congress on Computer Analysis of Images and Patterns, pp. 332\u2013339. (2011)","DOI":"10.1007\/978-3-642-23678-5_39"},{"key":"894_CR6","doi-asserted-by":"crossref","unstructured":"Hu, K., Yin, L.: Multi-scale topological features for hand posture representation and analysis. In: IEEE International Conference on Computer Vision (ICCV), 2013, pp. 1928\u20131935. (2013)","DOI":"10.1109\/ICCV.2013.242"},{"key":"894_CR7","doi-asserted-by":"crossref","unstructured":"Waltisberg, D., Yao, A., Gall, J., Van\u00a0Gool, L.: Variations of a Hough-voting action recognition system. In: \u00dcnay, D., \u00c7ataltepe, Z., Aksoy, S. (eds.) Recognizing Patterns in Signals, Speech, Images and Videos, pp. 306\u2013312. Springer, Berlin (2010)","DOI":"10.1007\/978-3-642-17711-8_31"},{"issue":"11","key":"894_CR8","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1109\/TPAMI.2011.70","volume":"33","author":"J Gall","year":"2011","unstructured":"Gall, J., Yao, A., Razavi, N., Van Gool, L., Lempitsky, V.: Hough forests for object detection, tracking, and action recognition. Pattern Anal. Mach. Intell. IEEE Trans. 33(11), 2188\u20132202 (2011)","journal-title":"Pattern Anal. Mach. Intell. IEEE Trans."},{"key":"894_CR9","doi-asserted-by":"crossref","unstructured":"Yao, A., Gall, J., Van\u00a0Gool, L.: A Hough transform-based voting framework for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 2061\u20132068. (2010)","DOI":"10.1109\/CVPR.2010.5539883"},{"issue":"3","key":"894_CR10","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), 299\u2013318 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"894_CR11","doi-asserted-by":"crossref","unstructured":"Nam, J., Alghoniemy, M., Tewfik, A.: Audio-visual content-based violent scene characterization. In: Proceedings of ICIP, pp. 353\u2013357. (1998)","DOI":"10.1109\/ICIP.1998.723496"},{"key":"894_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, W., Chu, W., Wu, J.L.: Semantic context detection based on hierarchical audio models. In: Proceedings of the ACM SIGMM Workshop on Multimedia Information Retrieval, New York, pp. 109\u2013115. (2003)","DOI":"10.1145\/973264.973282"},{"key":"894_CR13","first-page":"150","volume":"6","author":"C Clarin","year":"2005","unstructured":"Clarin, C., Dionisio, J., Echavez, M., Naval, P.: Dove: detection of movie violence using motion intensity analysis on skin and blood. PCSC 6, 150\u2013156 (2005)","journal-title":"PCSC"},{"key":"894_CR14","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Kosmopoulos, D., Aristidou, A., Theodoridis, S.: Violence content classification using audio features. In: Advances in Artificial Intelligence, Lecture Notes in Computer Science, vol. 3955, pp. 502\u2013507. (2006)","DOI":"10.1007\/11752912_55"},{"key":"894_CR15","doi-asserted-by":"crossref","unstructured":"Zajdel, W., Krijnders, J., Andringa, T., Gavrila, D.: CASSANDRA: audio-video sensor fusion for aggression detection. In: IEEE Conference on Advanced Video and Signal Based Surveillance, 2007, pp. 200\u2013205. (2007)","DOI":"10.1109\/AVSS.2007.4425310"},{"key":"894_CR16","doi-asserted-by":"crossref","unstructured":"Gong, Y., Wang, W., Jiang, S., Huang, Q., Gao, W.: Detecting violent scenes in movies by auditory and visual cues. In: Proceedings of the 9th Pacific Rim Conference on Multimedia, pp. 317\u2013326. Springer, Berlin (2008)","DOI":"10.1007\/978-3-540-89796-5_33"},{"key":"894_CR17","unstructured":"Chen, D., Wactlar, H., Chen, M., Gao, C., Bharucha, A., Hauptmann, A.: Recognition of aggressive human behavior using binary local motion descriptors. In: Engineering in Medicine and Biology Society, 2008. (20\u201325 2008) pp. 5238\u20135241 (2008)"},{"key":"894_CR18","doi-asserted-by":"crossref","unstructured":"Lin, J., Wang, W.: Weakly-supervised violence detection in movies with audio and video based co-training. In: Proceedings of the 10th Pacific Rim Conference on Multimedia, pp. 930\u2013935. Springer, Berlin (2009)","DOI":"10.1007\/978-3-642-10467-1_84"},{"key":"894_CR19","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Makris, A., Kosmopoulos, D., Perantonis, S., Theodoridis, S.: Audio-visual fusion for detecting violent scenes in videos. In: 6th Hellenic Conference on AI, SETN 2010, Athens, Greece, May 4\u20137, 2010. Proceedings, pp. 91\u2013100. Springer, London (2010)","DOI":"10.1007\/978-3-642-12842-4_13"},{"issue":"8","key":"894_CR20","first-page":"1161","volume":"25","author":"L Chen","year":"2011","unstructured":"Chen, L., Su, C., Hsu, H.: Violent scene detection in movies. IJPRAI 25(8), 1161\u20131172 (2011)","journal-title":"IJPRAI"},{"key":"894_CR21","doi-asserted-by":"crossref","unstructured":"Hassner, T., Itcher, Y., Kliper-Gross, O.: Violent flows: real-time detection of violent crowd behavior. In: 3rd IEEE International Workshop on Socially Intelligent Surveillance and Monitoring (SISM) at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2012)","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"894_CR22","unstructured":"Demarty, C., Penet, C., Gravier, G., Soleymani, M.: MediaEval 2012 affect task: violent scenes detection in Hollywood movies. In: MediaEval 2012 Workshop, Pisa (2012)"},{"issue":"8","key":"894_CR23","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1109\/TPAMI.2011.253","volume":"34","author":"RK Ward","year":"2012","unstructured":"Ward, R.K., Guha, T.: Learning sparse representations for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1576\u20131588 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"894_CR24","doi-asserted-by":"crossref","unstructured":"Mohammadi, S., Kiani, H., Perina, A., Murino, V.: Violence detection in crowded scenes using substantial derivative. In: International Conference on Advanced Video and Signal-based Surveillance, AVSS, (2015)","DOI":"10.1109\/AVSS.2015.7301787"},{"key":"894_CR25","unstructured":"Deniz, O., Serrano, I., Bueno, G., Kim, T.K.: Fast violence detection in video. In: The 9th International Conference on Computer Vision Theory and Applications (VISAPP), (2014)"},{"key":"894_CR26","unstructured":"Serrano, I., D\u00e9niz, O., Bueno, G.: Visilab at MediaEval 2013: fight detection. In: MediaEval 2013, vol. 1043. MediaEval Bechmark (2013)"},{"key":"894_CR27","doi-asserted-by":"crossref","unstructured":"Chen, M., Mummert, L., Pillai, P., Hauptmann, A., Sukthankar, R.: Exploiting multi-level parallelism for low-latency activity recognition in streaming video. In: MMSys \u201910: Proceedings of the First Annual ACM SIGMM Conference on Multimedia Systems, New York, pp. 1\u201312. (2010)","DOI":"10.1145\/1730836.1730838"},{"issue":"4","key":"894_CR28","doi-asserted-by":"crossref","first-page":"e0120448","DOI":"10.1371\/journal.pone.0120448","volume":"10","author":"I Serrano","year":"2015","unstructured":"Serrano, I., Deniz, O., Bueno, G., Kim, T.K.: Fast fight detection. PLoS ONE 10(4), e0120448 (2015)","journal-title":"PLoS ONE"},{"key":"894_CR29","unstructured":"Tobias, S., Volker, E., Thomas, S.: A local feature based on Lagrangian measures for violent video classification. In: 6th International Conference on Imaging for Crime Prevention and Detection, IET (2015)"},{"key":"894_CR30","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.imavis.2016.01.006","volume":"48","author":"Y Gao","year":"2016","unstructured":"Gao, Y., Liu, H., Sun, X., Wang, C., Liu, Y.: Violence detection using oriented violent flows. Image Vis. Comput. 48, 37\u201341 (2016)","journal-title":"Image Vis. Comput."},{"key":"894_CR31","unstructured":"Matikainen, P., Hebert, M., Sukthankar, R.: Trajectons: Action recognition through the motion analysis of tracked features. In: IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), 2009, pp. 514\u2013521. (2009)"},{"key":"894_CR32","doi-asserted-by":"crossref","unstructured":"Messing, R., Pal, C., Kautz, H.: Activity recognition using the velocity histories of tracked keypoints. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 104\u2013111. (2009)","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"894_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169\u20133176. (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"894_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 3551\u20133558. (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"894_CR35","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. D., Weinberger, K. Q. (eds.) Advances in Neural Information Processing Systems 27, pp.\u00a0568\u2013576. Curran Associates, Inc. (2014)"},{"key":"894_CR36","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4305\u20134314. (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"894_CR37","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497. (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"894_CR38","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005, pp. 65\u201372. (2005)","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"894_CR39","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3361\u20133368. (2011)","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"894_CR40","doi-asserted-by":"crossref","unstructured":"Taylor, G.W., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. In: Computer Vision\u2013ECCV 2010, pp. 140\u2013153. Springer, Berlin (2010)","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"894_CR41","doi-asserted-by":"crossref","unstructured":"Willems, G., Tuytelaars, T., Van\u00a0Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Computer Vision\u2013ECCV 2008, pp. 650\u2013663. Springer, Berlin (2008)","DOI":"10.1007\/978-3-540-88688-4_48"},{"issue":"1","key":"894_CR42","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"894_CR43","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In: IEEE International Conference on Computer Vision (ICCV), (2009)","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"894_CR44","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. (2008)","DOI":"10.1109\/CVPR.2008.4587756"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00138-017-0894-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-017-0894-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-017-0894-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,7]],"date-time":"2019-10-07T12:59:30Z","timestamp":1570453170000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00138-017-0894-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,7]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018,2]]}},"alternative-id":["894"],"URL":"https:\/\/doi.org\/10.1007\/s00138-017-0894-7","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2017,12,7]]}}}