2012 IEEE Conference on Computer Vision and Pattern Recognition (2012)
Providence, RI USA
June 16, 2012 to June 21, 2012
J. Ghosh , Univ. of Texas at Austin, Austin, TX, USA
Yong Jae Lee , Univ. of Texas at Austin, Austin, TX, USA
K. Grauman , Univ. of Texas at Austin, Austin, TX, USA
We developed an approach to summarize egocentric video. We introduced novel egocentric features to train a regressor that predicts important regions. Using the discovered important regions, our approach produces significantly more informative summaries than traditional methods that often include irrelevant or redundant information.
video signal processing, feature extraction, object detection, important region discovery, egocentric video summarization, egocentric features, informative summaries, important object discovery, important people discovery, Cameras, Visualization, Predictive models, Image color analysis, Training, Context, Humans
J. Ghosh, Yong Jae Lee and K. Grauman, "Discovering important people and objects for egocentric video summarization," 2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Providence, RI USA, 2012, pp. 1346-1353.