{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T04:27:12Z","timestamp":1768969632786,"version":"3.49.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2011,5,28]],"date-time":"2011-05-28T00:00:00Z","timestamp":1306540800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2012,9]]},"DOI":"10.1007\/s11042-011-0817-y","type":"journal-article","created":{"date-parts":[[2011,5,27]],"date-time":"2011-05-27T12:10:44Z","timestamp":1306498244000},"page":"233-255","source":"Crossref","is-referenced-by-count":24,"title":["HMM based soccer video event detection using enhanced mid-level semantic"],"prefix":"10.1007","volume":"60","author":[{"given":"Xueming","family":"Qian","sequence":"first","affiliation":[]},{"given":"Huan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guizhong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xingsong","family":"Hou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,5,28]]},"reference":[{"issue":"4","key":"817_CR1","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.cviu.2003.06.004","volume":"6","author":"J Assfalg","year":"2003","unstructured":"Assfalg J, Bertini M, Colombo C, Bimbo A, Nunziati W (2003) Semantic annotation of soccer videos: automatic highlight identification. Comput Vis Image Underst 6(4):285\u2013305","journal-title":"Comput Vis Image Underst"},{"key":"817_CR2","doi-asserted-by":"crossref","unstructured":"Chen S, Chen M, Zhang C, Shyu M (2006). Exciting event detection using multi-level multimodal descriptors and data classification. in Proc. ISM.","DOI":"10.1109\/ISM.2006.73"},{"issue":"3","key":"817_CR3","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1109\/TMM.2006.870726","volume":"8","author":"C Cheng","year":"2006","unstructured":"Cheng C, Hsu C (2006) Fusion of audio and motion information on HMM-based highlight extraction for baseball games. IEEE Trans Multimedia 8(3):585\u2013599","journal-title":"IEEE Trans Multimedia"},{"key":"817_CR4","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histogram of oriented gradients for human detection. In Proc. Int. Conf. Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2005.177"},{"key":"817_CR5","unstructured":"Dao M, Babaguchi N (2008) Mining temporal information and web-casting text for automatic sports event detection. In Proc. MMSP, pp.616\u2013621"},{"key":"817_CR6","doi-asserted-by":"crossref","unstructured":"Dao M, Babaguchi N (2008) Sports event detection using temporal patterns mining and web-casting text. In Proc. ACM AREA, pp. 33\u201340","DOI":"10.1145\/1463542.1463549"},{"key":"817_CR7","doi-asserted-by":"crossref","unstructured":"Duan L, Xu M, Chua T, Tian Q, Xu C (2003) A mid-level representation framework for semantic sports video analysis. In Proc. ACM Multimedia, pp. 29\u201332","DOI":"10.1145\/957013.957020"},{"key":"817_CR8","unstructured":"Duan L, Xu M, Tian Q (2003) Semantic shot classification in sports video. In Proc. SPIE Storage and Retrieval for Media Database 5021:300\u2013313"},{"issue":"6","key":"817_CR9","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1109\/TMM.2005.858395","volume":"7","author":"L Duan","year":"2005","unstructured":"Duan L, Xu M, Tian Q, Xu C, Jin JS (2005) A unified framework for semantic shot classification in sports video. IEEE Trans Multimedia 7(6):1066\u20131083","journal-title":"IEEE Trans Multimedia"},{"key":"817_CR10","unstructured":"Ekin A, Tekalp A (2003) Generic play-break event detection for summarization and hierarchical sports video analysis. In Proc. Int. Conf. Mulmedia and Expo 1:169\u2013172"},{"issue":"7","key":"817_CR11","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/TIP.2003.812758","volume":"12","author":"A Ekin","year":"2003","unstructured":"Ekin A, Tekalp A, Mehrotra R (2003) Automatic soccer video analysis and summarization. IEEE Trans Image Process 12(7):796\u2013807","journal-title":"IEEE Trans Image Process"},{"key":"817_CR12","unstructured":"Hanjialic A (2003) Generic approach to highlights extraction from a sports video. In Proc. Int. Conf. Image Processing 1: 1\u20134"},{"issue":"4","key":"817_CR13","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/TMM.2006.876289","volume":"8","author":"C Huang","year":"2006","unstructured":"Huang C, Shih H, Chao C (2006) Semantic analysis of soccer video using dynamic Bayesian network. IEEE Trans Multimedia 8(4):749\u2013760","journal-title":"IEEE Trans Multimedia"},{"key":"817_CR14","doi-asserted-by":"crossref","unstructured":"Jin G, Tao L, Xu G (2004) Hidden markov model based events detection in soccer video. ICIAR 2004, LNCS 3221:605\u2013612","DOI":"10.1007\/978-3-540-30125-7_75"},{"key":"817_CR15","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/j.jvcir.2004.04.006","volume":"17","author":"B Li","year":"2004","unstructured":"Li B, Errico J, Pan H, Sezan M (2004) Bridging the semantic gap in sports video retrieval and summarization. J Vis Commun Image R 17:393\u2013424","journal-title":"J Vis Commun Image R"},{"key":"817_CR16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jvcir.2006.09.002","volume":"18","author":"C Lien","year":"2007","unstructured":"Lien C, Chiang C, Lee C (2007) Scene-based event detection for baseball videos. J Vis Commun Image R 18:1\u201314","journal-title":"J Vis Commun Image R"},{"issue":"2","key":"817_CR17","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1109\/TCSVT.2004.841653","volume":"15","author":"M Lyu","year":"2005","unstructured":"Lyu M, Song J, Cai M (2005) A comprehensive method for multilingual video text detection, localization, and extraction. IEEE Trans Circ Syst Video Technol 15(2):243\u2013255","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"817_CR18","doi-asserted-by":"crossref","unstructured":"Mittal A, Cheong L, Leung T (2001) Dynamic bayesian framework for extracting temporal structure in video. In Proc. Int. Conf. Computer Vision and Pattern Recognition, pp. 110\u2013115","DOI":"10.1109\/CVPR.2001.990933"},{"key":"817_CR19","doi-asserted-by":"crossref","unstructured":"Nan N, Liu G, Qian X, Wang C (2008) An SVM-based soccer video shot classification scheme using projection histograms. PCM","DOI":"10.1007\/978-3-540-89796-5_105"},{"key":"817_CR20","unstructured":"[online] http:\/\/worldcup.qq.com\/zt2010\/zongjie\/index.htm"},{"key":"817_CR21","doi-asserted-by":"crossref","unstructured":"Pan H, Beek P, Sezan M (2001) Detection of slow-motion replay segments in sports video for highlights generation. In Proc. Int. Conf. Acoustics, Speech, and Signal Processing 3:1649\u20131652, Salt Lake City, USA, May, 2001","DOI":"10.1109\/ICASSP.2001.941253"},{"key":"817_CR22","unstructured":"Pan H, Li B, Sezan M (2002). Automatic detection of replay segments in broadcast sports programs by detecting of logos in scene transitions. In Proc. Int. Conf. Acoustics, Speech, and Signal Processing 4:3385\u20133388, Orlando, FL, May 2002"},{"key":"817_CR23","doi-asserted-by":"crossref","unstructured":"Papadopoulos G, Mezaris V, Kompatsiaris I, Strintzis M (2008) Accumulated motion energy fields estimation and representation for semantic event detection. In Proc. CIVR, pp. 221-230","DOI":"10.1145\/1386352.1386385"},{"key":"817_CR24","doi-asserted-by":"crossref","unstructured":"Qian X, Liu G (2007) Global motion estimation from randomly selected motion vector groups and GM\/LM based applications. Signal, Image and Video Processing","DOI":"10.1007\/s11760-007-0004-9"},{"key":"817_CR25","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1016\/j.image.2007.06.005","volume":"22","author":"X Qian","year":"2007","unstructured":"Qian X, Liu G, Wang H, Su R (2007) Text detection, localization and tracking in compressed videos. Signal Process Image Commun 22:752\u2013768","journal-title":"Signal Process Image Commun"},{"key":"817_CR26","doi-asserted-by":"crossref","unstructured":"Qian X, Liu G, Guo D, Li Z, Wang Z, Wang H (2009) Object categorization using hierarchical wavelet packet texture descriptors. In Proc. ISM, pp. 44\u201351","DOI":"10.1109\/ISM.2009.14"},{"key":"817_CR27","doi-asserted-by":"crossref","unstructured":"Qian X, Wang H, Liu G, Li Z, Wang Z (2010) Soccer video event detection by fusing middle level visual semantics of an event clip. In Proc. PCM, pp. 439\u2013451","DOI":"10.1007\/978-3-642-15696-0_41"},{"key":"817_CR28","doi-asserted-by":"crossref","unstructured":"Qian X, Liu G, Wang Z, Li Z, Wang H (2010) Highlight events detection in soccer video using HCRF. In Proc. ICIMCS","DOI":"10.1145\/1937728.1937769"},{"issue":"2","key":"817_CR29","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L Rabiner","year":"1989","unstructured":"Rabiner L (1989) A tutorial on hidden markov models and selected applications in speech recognition. Proc IEEE 77(2):257\u2013285","journal-title":"Proc IEEE"},{"issue":"10","key":"817_CR30","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1109\/TCSVT.2005.854237","volume":"15","author":"D Sadlier","year":"2005","unstructured":"Sadlier D, O\u2019Connor N (2005) Event detection in field sports video using audio-visual features and a support vector Machine. IEEE Trans Circuits Syst Video Technol 15(10):602\u2013615","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"4","key":"817_CR31","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1109\/TMM.2005.850966","volume":"7","author":"C Snoek","year":"2005","unstructured":"Snoek C, Worring M (2005) Multimedia event-based video indexing using time intervals. IEEE Trans Multimedia 7(4):638\u2013647","journal-title":"IEEE Trans Multimedia"},{"issue":"2","key":"817_CR32","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1109\/TCSVT.2004.841656","volume":"15","author":"Y Su","year":"2005","unstructured":"Su Y, Sun M, Hsu V (2005) Global motion estimation from coarsely sampled motion vector field and the applications. IEEE Trans Circuits Syst Video Technol 15(2):232\u2013242","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"817_CR33","doi-asserted-by":"crossref","unstructured":"Tjondronegoro DW, Chen Y, Pham B (2004) Classification of self-consumable highlights for soccer video summaries. In Proc. Int. Conf. Mulmedia and Expo pp. 579\u2013582","DOI":"10.1109\/ICME.2004.1394258"},{"key":"817_CR34","unstructured":"Wang Y, Liu Z, Huang J (2000) Multimedia content analysis using both audio and video clues. IEEE Signal Processing Magazine"},{"key":"817_CR35","unstructured":"Wang F, Ma Y, Zhang H, Li J (2004) Dynamic Bayesian network based event detection for soccer highlight extraction. In Proc. Int. Conf. Image Processing, pp. 633\u2013636"},{"key":"817_CR36","doi-asserted-by":"crossref","unstructured":"Wang F, Ma Y, Zhang H, Li J (2005) A generic framework for semantic sports video analysis using dynamic Bayesian networks. In Proc. Int. Conf. Multimedia Modelling, pp. 29\u201332","DOI":"10.1109\/MMMC.2005.9"},{"key":"817_CR37","unstructured":"Wang T, Li J, Diao Q, Hu W, Zhang Y, Dulong C (2006) Semantic event detection using conditional random fields. In Proc. Computer Vision and Pattern Recognition Workshop, pp. 109\u2013115"},{"key":"817_CR38","doi-asserted-by":"crossref","unstructured":"Wickramaratna K, Chen M, Chen S, Shyu M (2005) Neural network based framework for goal event detection in soccer videos. In Proc. Int. Symposium on Multimedia. pp. 21\u201328","DOI":"10.1109\/ISM.2005.83"},{"key":"817_CR39","doi-asserted-by":"crossref","unstructured":"Xie L, Chang S, Divakaran A, Sun H (2002) Structure analysis of soccer video with hidden Markov models. In Proc. Int. Conf. Acoustics, Speech, and Signal Processing, pp. 4096\u20134099","DOI":"10.1109\/ICASSP.2002.5745558"},{"key":"817_CR40","unstructured":"Xiong Z, Radhakrishnan R, Divakaran A, Huang T (2005) Highlights extraction from sports video based on an audio-visual marker detection framework. In Proc. Int. Conf. Multimedia & Expo, pp. 29\u201332"},{"key":"817_CR41","unstructured":"Xu P, Xie L, Chang S (2001) Algorithms and systems for segmentation and structure analysis in soccer video. In Proc. Int. Conf. Multimedia & Expo, pp. 184\u2013187."},{"issue":"3","key":"817_CR42","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1109\/TMM.2008.917346","volume":"10","author":"C Xu","year":"2008","unstructured":"Xu C, Wang J, Lu H, Zhang Y (2008) A novel framework for semantic annotation and personalized retrieval of sports video. IEEE Trans Multimedia 10(3):421\u2013436","journal-title":"IEEE Trans Multimedia"},{"issue":"7","key":"817_CR43","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1109\/TMM.2008.2004912","volume":"10","author":"C Xu","year":"2008","unstructured":"Xu C, Zhang Y, Zhu G, Rui Y, Lu H, Huang Q (2008) Using webcast text for semantic event detection in broadcast sports video. IEEE Trans Multimedia 10(7):1342\u20131325","journal-title":"IEEE Trans Multimedia"},{"issue":"11","key":"817_CR44","doi-asserted-by":"crossref","first-page":"1422","DOI":"10.1109\/TCSVT.2005.856903","volume":"15","author":"G Xu","year":"2005","unstructured":"Xu G, Ma Y, Zhang H, Yang S (2005) An HMM-based framework for video semantic analysis. IEEE Trans Circ Syst Video Technol 15(11):1422\u20131433","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"817_CR45","doi-asserted-by":"crossref","unstructured":"Zhang D, Chang S (2002) Event detection in baseball video using superimposed caption recognition. In Proc. ACM Multimedia, Juan-les- Pins, France, Nov. 1, pp. 315\u2013318","DOI":"10.1145\/641007.641073"},{"key":"817_CR46","doi-asserted-by":"crossref","unstructured":"Zhao Z, Jiang S, Huang Q, Zhu G (2006) Highlight summarization in sports video based on replay detection. In Proc. Int. Conf. Mulmedia and Expo pp. 1613\u20131616, Toronto, Ontario, Canada, July 2006","DOI":"10.1109\/ICME.2006.262855"},{"issue":"5","key":"817_CR47","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1109\/TKDE.2005.83","volume":"17","author":"X Zhu","year":"2005","unstructured":"Zhu X, Wu X, Elmagarmid A, Feng Z, Wu L (2005) Video data mining semantic indexing and event detection from the association perspective. IEEE Trans Knowl Data Eng 17(5):665\u2013677","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"817_CR48","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1109\/TMM.2008.2008918","volume":"11","author":"G Zhu","year":"2009","unstructured":"Zhu G, Xu C, Huang Q, Rui Y, Jiang S, Gao W, Yao H (2009) Event tactic analysis based on broadcast sport video. IEEE Trans Multimedia 11(1):49\u201367","journal-title":"IEEE Trans Multimedia"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-011-0817-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-011-0817-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-011-0817-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,11]],"date-time":"2019-06-11T07:26:48Z","timestamp":1560238008000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-011-0817-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,5,28]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,9]]}},"alternative-id":["817"],"URL":"https:\/\/doi.org\/10.1007\/s11042-011-0817-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,5,28]]}}}