Event/object classification and recognition is an extremely challenging problem, particularly when the query or stored data undergo an affine transformation due to camera motion. ...
This paper presents a framework for directly addressing issues arising from self-occlusions and ambiguities due to the lack of depth information in vector-based representations. V...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
Abstract. This paper proposes a novel method to deal with the representation issue in texture classification. A learning framework of image descriptor is designed based on the Fish...
VLFeat is an open and portable library of computer vision algorithms. It aims at facilitating fast prototyping and reproducible research for computer vision scientists and student...