The video track is added into TREC-10, composed of two tasks, automatic shot boundary detection and video retrieval. In this year, we (MSR-Asia) participated in the video track, f...
The concept of a documentary scene was inferred from the audio-visual characteristics of certain documentary videos. It was observed that the amount of information from the visual ...
Video parsing refers to the detection of scene changes and special e ects in the video stream and is used to extract key frames from a video stream. In this paper, we propose paral...
Suchendra M. Bhandarkar, Shankar R. Chandrasekaran
In this paper, we present a computational scene model and also derive novel algorithms for computing audio and visual scenes and within-scene structures in films. We use constraint...