Most current image retrieval systems and commercial search engines use mainly text annotations to index and retrieve WWW images. This research explores the use of machine learning...
Content-aware resizing methods have recently been developed, among which, seam-carving has achieved the most widespread use. Seam-carving's versatility enables deliberate obj...
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...
This paper gives an overview of works done in our group on 3D and appearance modeling of objects, from images. The backbone of our approach is to use what we consider as the princi...
One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performa...