This paper presents a framework for image parsing with multiple label sets. For example, we may want to simultaneously label every image region according to its basiclevel object ...
This paper proposes a new method to synthesize and inpaint geometric textures. The texture model is composed of a geometric layer that drives the computation of a new grouplet tran...
This paper presents a new approach to single-image superresolution, based on sparse signal representation. Research on image statistics suggests that image patches can be wellrepre...
Jianchao Yang, John Wright, Thomas S. Huang, Yi Ma
Experiments have shown [2] that we can only memorize images up to a certain complexity level, after which, instead of memorizing the image itself, we, sort of, memorize a probabil...
Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtaine...