The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
We present a novel method to obtain a 3D Euclidean reconstruction of both the background and moving objects in a video sequence. We assume that, multiple objects are moving rigidl...
This paper describes an approach for generating Binary Partition Tree [7] representations and video object segmentations using a novel region merging strategy based on motion simi...
This paper describes a technique, called V-Mirroring, for integrating videos taken from different cameras with different viewpoints of the same scene. The term V-Mirroring stems f...
This paper proposes a motion-focusing method to extract key frames and generate summarization synchronously for surveillance videos. Within each pre-segmented video shot, the prop...