Affective sports highlight detection

Abstract

This paper explores a psychological attention approach for sports highlight detection. A multiresolution autoregressive algorithm is proposed to fuse misaligned audio-visual time sequences and estimate an unified attention curve. Game highlights are found by ranking attention intensity; content-based events are filtered out by allocating local attention peaks. The test bed includes six complete football games from World Cup 2002, 2006 and Champion League 2006, and two content suppliers, BBC and ITV. Two evaluations are presented, the comparison on average attention and event attention, and the ranking of goal events. Experiments show this fusion framework is robust on different data collections.