<XML><RECORDS><RECORD><REFERENCE_TYPE>3</REFERENCE_TYPE><REFNUM>7571</REFNUM><AUTHORS><AUTHOR>Baillie,M.</AUTHOR><AUTHOR>Jose,J.M.</AUTHOR><AUTHOR>van Rijsbergen,C.J.</AUTHOR></AUTHORS><YEAR>2004</YEAR><TITLE>HMM Model Selection Issues for Soccer video</TITLE><PLACE_PUBLISHED> In the 3rd International Conference of Image and Video Retrieval (CIVR2004) Dublin, Ireland </PLACE_PUBLISHED><PUBLISHER>Springer</PUBLISHER><LABEL>Baillie:2004:7571</LABEL><ABSTRACT>There has been a concerted effort from the Video Retrieval community to develop tools that automate the annotation process of Sports video. In this paper, we provide an in-depth investigation into three Hidden Markov Model (HMM) selection approaches. Where HMM, a popular indexing framework, is often applied in a ad hoc manner. We investigate what effect, if any, poor HMM selection can have on future indexing performance when classifying specific audio content. Audio is a rich source of information that can provide an effective alternative to high dimensional visual or motion based features. As a case study, we also illustrate how a superior HMM framework optimised using a Bayesian HMM selection strategy, can both segment and then classify Soccer video, yielding promising results. </ABSTRACT></RECORD></RECORDS></XML>