Company News

Optimal Depth Recovery using Image Guided TGV with Depth Confidence for High-Quality View Synthesis

|

Pongsak Lasang, Wuttipong Kumwilaisak, Yazhou Liu and Shengmei Shen
Journal of Visual Communication and Image Representation, 2016.05

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.

Link: https://dl.acm.org/citation.cfm?id=2984061