We develop a robust technique to find similar matches of human actions in video. Given a query video, Motion History Images (MHI) are constructed for consecutive keyframes. This i...
This paper proposes a robust video fingerprinting method based on 2-Dimensional Oriented Principal Component Analysis (2D-OPCA) of affine covariant regions. The goal of video fing...
We present an approach to discover and segment foreground object(s) in video. Given an unannotated video sequence, the method first identifies object-like regions in any frame a...
In this paper we proposed a video signature based on ordinal measure of resampled video frames, which is robust to changing compression formats, compression ratios, frame sizes an...
In this work, we address the problem of building recognition across two camera views with large changes in scales and viewpoints. The main idea is to construct a semantically rich...