Research Article
Attention guided football video content recommendation on mobile devices
@INPROCEEDINGS{10.1145/1374296.1374330, author={Reede Ren and Joemon M. Jose }, title={Attention guided football video content recommendation on mobile devices}, proceedings={2nd International ICST Conference on Mobile Multimedia Communications}, publisher={ACM}, proceedings_a={MOBIMEDIA}, year={2006}, month={9}, keywords={Attention feature audio-visual fusion linear prediction and sports video retrieval}, doi={10.1145/1374296.1374330} }- Reede Ren
Joemon M. Jose
Year: 2006
Attention guided football video content recommendation on mobile devices
MOBIMEDIA
ACM
DOI: 10.1145/1374296.1374330
Abstract
Live football video is the major content genre in 3G mobile service. In this paper, we introduce a realtime general highlight detection algorithm based on attention analysis. It combines attention-related media modalities into role-based attention curves, namely video director, spectator and commentator, to track viewers' feeling against game content from media data. A series of linear temporal predictors are assumed from video data directly and employed to allocate strong attention changes, which are marked as scroll-back endpoints for mobile video skim. The advantages of our algorithm are that it avoids semantic uncertainty of game highlights and that it requires little training. We evaluated our approach using the test bed with full five games from different content suppliers to prove the robustness.
