Human faces are neither exactly Lambertian nor entirely convex and hence most models in literature which make the Lambertian assumption, fall short when dealing with specularities...
Angelos Barmpoutis, Ritwik Kumar, Baba C. Vemuri, ...
A novel shape descriptor, which can be extracted from the major object edges automatically and used for the multimedia content-based retrieval in multimedia databases, is presented...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
In this paper, we present a method using pixel-level information, local region-level information and global-level information to remove shadow. At the pixel-level, we employ GMM t...
Zhou Liu, Kaiqi Huang, Tieniu Tan, Liangsheng Wang
In this paper, we describe a local safety knowledge sharing system among the community. Our system makes it possible to share detailed safety knowledge, which includes location an...