REPLAY SCENE CLASSIFICATION IN SOCCER VIDEO USING WEB BROADCAST TEXT (WedPmPO1)

Author(s) : Jinhui Dai (Chinese Academy of Sciences, China) Lingyu Duan (Institute for Infocomm Research, Singapore) Xiaofeng Tong (Chinese Academy of Sciences, China) Changsheng Xu (Institute for Infocomm Research, Singapore) Qi Tian (Institute for Infocomm Research, Singapore) Hanqing Lu (Chinese Academy of Sciences, China) Jesse Jin (University of Newcastle, Australia)

Abstract : The automatic extraction of sports video highlights is a typical kind of personalized media production process. Many ways have been studied from the viewpoints of low-level au-dio/visual processing (e.g. detection of excited commentator speech), event detection (e.g. goal detection), etc. However, the subjectivity of highlights is an unavoidable bottleneck. The replay scene is an effective clue for highlights in broad-cast sports video due to the incorporation of video produc-tion knowledge. Most related work deals with the replay de-tection and/or a simple composition of all detected replays to generate highlights. Different from previous work, our work considers different flavors of different people in terms of highlight content or type through replay scenes classification. The main contributions include: 1) proposing a multi-modal (visual+textual) approach for refined replay classification; 2) employing the sources of Broadcast Web Text (BWT) to fa-cilitate replay content analysis. An overall accuracy of 79.9% has been achieved on seven soccer matches over seven replay categories.

Menu