Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional ...
—We present in this paper an integrated solution to rapidly recognizing dynamic objects in surveillance videos by exploring various contextual information. This solution consists...
Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, We...
A common design of an object recognition system has
two steps, a detection step followed by a foreground withinclass
classification step. For example, consider face detection
by...
Abstract. In this paper we propose a probabilistic framework that models shape variations and infers dense and detailed 3D shapes from a single silhouette. We model two types of sh...
Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language pr...