{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T16:04:40Z","timestamp":1779984280112,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,10,19]],"date-time":"2009-10-19T00:00:00Z","timestamp":1255910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,10,19]]},"DOI":"10.1145\/1631272.1631297","type":"proceedings-article","created":{"date-parts":[[2009,10,20]],"date-time":"2009-10-20T08:43:40Z","timestamp":1256028220000},"page":"165-174","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":39,"title":["Detecting video events based on action recognition in complex scenes using spatio-temporal descriptor"],"prefix":"10.1145","author":[{"given":"Guangyu","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihong","family":"Gong","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2009,10,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459392"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.85"},{"key":"e_1_3_2_1_3_1","first-page":"1","volume-title":"Int. Conf. Computer Vision and Pattern Recognition","author":"Xu D.","year":"2007","unstructured":"D. Xu and S.F Chang, \"Visual event recognition in news video using kernel methods with multi-level temporal alignment,\" in Proc. Int. Conf. Computer Vision and Pattern Recognition, 2007, pp. 1--8."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.946990"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180728"},{"key":"e_1_3_2_1_6_1","first-page":"1","volume-title":"Int. Conf. Computer Vision","author":"Ke Y.","year":"2007","unstructured":"Y. Ke, R. Sukthankar, and M. Hebert, \"Event detection in crowded videos,\" in Proc. Int. Conf. Computer Vision, 2007, pp. 1--8."},{"key":"e_1_3_2_1_7_1","first-page":"1","volume-title":"Int. Conf. Computer Vision and Pattern Recognition","author":"Laptev I.","year":"2008","unstructured":"I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld, \"Learning realistic human actions from movies,\" in Proc. Int. Conf. Computer Vision and Pattern Recognition, 2008, pp. 1--8."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1018429.1020906"},{"key":"e_1_3_2_1_9_1","unstructured":"TREC Video Retrieval Evaluation http:\/\/www-nlpir.nist.gov\/projects\/trecvid. http:\/\/www.itl.nist.gov\/iad\/mig\/\/tests\/trecvid\/2008\/doc\/EventDet08-EvalPlan-v07.htm. http:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv8.slides\/event-detection.pdf."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459456"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0262-8856(02)00127-0"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2004.829274"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005607"},{"key":"e_1_3_2_1_14_1","first-page":"189","volume-title":"Int. Conf. Acoustics, Speech, and Signal Processing","volume":"3","author":"Xu M.","year":"2003","unstructured":"M. Xu, L. Duan, C. Xu, and Q. Tian, \"A fusion scheme of visual and auditory modalities for event detection in sports video,\" in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, vol. 3, 2003, pp. 189--192."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.830811"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180699"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2004.01.005"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911830"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.850966"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.854237"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005594"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_23_1","first-page":"864","volume-title":"Int. Conf. Computer Vision and Pattern Recognition","author":"Han M.","year":"2004","unstructured":"M. Han, W. Xu, H. Tao, and Y. Gong, \"An algorithm for multiple object trajectory tracking,\" in Proc. Int. Conf. Computer Vision and Pattern Recognition, 2004, pp. 864--871."},{"key":"e_1_3_2_1_24_1","volume-title":"Int. Conf. Computer Vision","author":"Yang M.","year":"2009","unstructured":"M. Yang, F. Lv, W. Xu, and Y. Gong, \"Detection driven adaptive multi-cue integration for multiple human tracking,\" in Proc. Int. Conf. Computer Vision, 2009."},{"key":"e_1_3_2_1_25_1","volume-title":"Math handbook for scientists and engineers","author":"Korn G.A.","year":"1968","unstructured":"G.A. Korn and T.M. Korn, Math handbook for scientists and engineers, New York: McGraw-Hill, 1968."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1057"},{"key":"e_1_3_2_1_27_1","first-page":"1","volume-title":"Int. Conf. Computer Vision","author":"Jhuang H.","year":"2007","unstructured":"H. Jhuang, T. Serre, L. Wolf, and T. Poggio, \"A biologically inspired system for action recognition,\" in Proc. Int. Conf. Computer Vision, 2007, pp. 1--8."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/211359"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282352"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/946247.946720"},{"key":"e_1_3_2_1_33_1","volume-title":"in Advances in Large Margin Classifiers","author":"Platt J.C.","year":"1999","unstructured":"J.C. Platt, \"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods\", in Advances in Large Margin Classifiers, Cambridge: MIT Press, 1999."},{"key":"e_1_3_2_1_34_1","volume-title":"Pattern classification and scene analysis","author":"Duda R.","year":"1973","unstructured":"R. Duda and P. Hart, Pattern classification and scene analysis, New York: John Wiley&Sons Inc, 1973."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"e_1_3_2_1_36_1","volume-title":"TRECVid workshop","author":"Lv F.","year":"2008","unstructured":"F. Lv, W. Xu, M, Yang, K. Yu, G. Zhu, and Y. Gong, \"Surveillance event detection,\" TRECVid notebook paper in Proc. TRECVid workshop, 2008."}],"event":{"name":"MM09: ACM Multimedia Conference","location":"Beijing China","acronym":"MM09","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 17th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1631272.1631297","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1631272.1631297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T15:23:01Z","timestamp":1779981781000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1631272.1631297"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,10,19]]},"references-count":36,"alternative-id":["10.1145\/1631272.1631297","10.1145\/1631272"],"URL":"https:\/\/doi.org\/10.1145\/1631272.1631297","relation":{},"subject":[],"published":{"date-parts":[[2009,10,19]]},"assertion":[{"value":"2009-10-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}