Previous works have demonstrated that the face recognition performance can be improved significantly in low dimensional linear subspaces. Conventionally, principal component analy...
We propose using multi-layer multiple instance learning (MMIL) for image set classification and applying it to the task of cannabis website classification. We treat each image as a...
Segmentation of surgical devices in fluoroscopic images and in particular of guide-wires is a valuable element during surgery. In cardiac angioplasty, the problem is particularly ...
We have proposed a complete system for text detection and localization in gray scale scene images. A boosting framework integrating feature and weak classifier selection based on...
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...