We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vecto...
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
We present a new approach to robust pose-variant face
recognition, which exhibits excellent generalization ability
even across completely different datasets due to its weak
depe...
John Wright (University of Illinois), Gang Hua (Mi...
We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized corre...
Kernel descriptors provide a unified way to generate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object rec...
Liefeng Bo, Kevin Lai, Xiaofeng Ren and Dieter Fox