Title :
Fast lead star detection in entertainment videos
Author :
Manickam, Nithya ; Chandran, Sharat
Author_Institution :
Dept. of Comput. Sci. & Eng., Indian Inst. of Technol. Bombay, Mumbai, India
Abstract :
Video can be summarized in many forms. One natural possibility that has been well explored is extracting key frames in shots or scenes, and then creating thumbnails. Another natural alternative that has been surprisingly ill-explored is to locate ¿lead stars¿ around whom the action revolves. Though scarce and far between, available techniques for detecting lead stars is usually video specific. In this paper, we highlight the importance of lead star detection, and present a generalized method for detecting snippets around lead actors in entertainment videos. Applications that naturally make use of this method include locating action around the `player of the match´ in sports videos, lead actors in movies and TV shows, and guest-host snippets in TV talk shows. Additionally, our method is considerably faster than the state-of-art spectral clustering technique with comparable accuracy.
Keywords :
entertainment; feature extraction; object detection; video signal processing; entertainment videos; key frame extraction; lead star detection; snippet detection; spectral clustering technique; sports videos; video summarization; Clustering algorithms; Computer science; Face detection; Layout; Motion detection; Motion pictures; Runtime; TV; Videos; Watches;
Conference_Titel :
Applications of Computer Vision (WACV), 2009 Workshop on
Conference_Location :
Snowbird, UT
Print_ISBN :
978-1-4244-5497-6
DOI :
10.1109/WACV.2009.5403086