Title :
Discovering important people and objects for egocentric video summarization
Author :
Lee, Yong Jae ; Ghosh, Joydeep ; Grauman, Kristen
Author_Institution :
Univ. of Texas at Austin, Austin, TX, USA
Abstract :
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.
Keywords :
feature extraction; object detection; video signal processing; egocentric features; egocentric video summarization; important object discovery; important people discovery; important region discovery; informative summaries; Cameras; Context; Humans; Image color analysis; Predictive models; Training; Visualization;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1226-4
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2012.6247820