Abstract | ||
---|---|---|
This paper describes our proposed method targeting at the MSR Image Recognition Challenge MS-Celeb-1M. The challenge is to recognize one million celebrities from their face images captured in the real world. The challenge provides a large scale dataset crawled from the Web, which contains a large number of celebrities with many images for each subject. Given a new testing image, the challenge requires an identify for the image and the corresponding confidence score. To complete the challenge, we propose a two-stage approach consisting of data cleaning and multi-view deep representation learning. The data cleaning can effectively reduce the noise level of training data and thus improves the performance of deep learning based face recognition models. The multi-view representation learning enables the learned face representations to be more specific and discriminative. Thus the difficulties of recognizing faces out of a huge number of subjects are substantially relieved. Our proposed method achieves a coverage of 46.1% at 95% precision on the random set and a coverage of 33.0% at 95% precision on the hard set of this challenge. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2964284.2984061 | ACM Multimedia |
Field | DocType | Citations |
Confidence score,Training set,Computer vision,Facial recognition system,Three-dimensional face recognition,Computer science,Noise level,Artificial intelligence,Deep learning,Discriminative model,Feature learning,Machine learning | Conference | 15 |
PageRank | References | Authors |
0.69 | 3 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jianshu Li | 1 | 141 | 12.04 |
Jian Zhao | 2 | 68 | 7.63 |
Fang Zhao | 3 | 46 | 4.03 |
Hao Liu | 4 | 28 | 2.59 |
Jing Li | 5 | 15 | 5.76 |
Sheng Mei Shen | 6 | 131 | 13.13 |
Jiashi Feng | 7 | 2165 | 140.81 |
Terence Sim | 8 | 2562 | 169.42 |