LI: COMPACT VIDEO CODE FOR ROBUST FACE RETRIEVAL IN TV-SERIES 1 Compact Video Code and Its Application to Robust Face Retrieval in TV-Series
BibTeX
@MISC{Li_li:compact,
author = {Yan Li and Ruiping Wang and Zhen Cui and Shiguang Shan and Xilin Chen},
title = {LI: COMPACT VIDEO CODE FOR ROBUST FACE RETRIEVAL IN TV-SERIES 1 Compact Video Code and Its Application to Robust Face Retrieval in TV-Series},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We address the problem of video face retrieval in TV-Series which searches video clips based on the presence of specific character, given one video clip of his/hers. This is tremendously challenging because on one hand, faces in TV-Series are captured in large-ly uncontrolled conditions with complex appearance variations, and on the other hand retrieval task typically needs efficient representation with low time and space complexi-ty. To handle this problem, we propose a compact and discriminative representation for the huge body of video data, named Compact Video Code (CVC). Our method first mod-els the video clip by its sample (i.e., frame) covariance matrix to capture the video data variations in a statistical manner. To incorporate discriminative information and obtain more compact video signature, the high-dimensional covariance matrix is further encod-ed as a much lower-dimensional binary vector, which finally yields the proposed CVC. Specifically, each bit of the code, i.e., each dimension of the binary vector, is produced via supervised learning in a max margin framework, which aims to make a balance be-tween the discriminability and stability of the code. Face retrieval experiments on two challenging TV-Series video databases demonstrate the competitiveness of the proposed CVC over state-of-the-art retrieval methods. In addition, as a general video matching algorithm, CVC is also evaluated in traditional video face recognition task on a standard Internet database, i.e., YouTube Celebrities, showing its quite promising performance by using an extremely compact code with only 128 bits. 1
Keyphrases
compact video code video clip robust face retrieval youtube celebrity state-of-the-art retrieval method face retrieval experiment tv-series video general video compact code video face retrieval traditional video face recognition task hand retrieval task low time large-ly uncontrolled condition discriminative information standard internet database specific character space complexi-ty binary vector discriminative representation max margin framework video data variation huge body covariance matrix quite promising performance compact video signature efficient representation complex appearance variation much lower-dimensional binary vector video data statistical manner high-dimensional covariance matrix supervised learning
