In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
This paper proposes to combine spatial and color coherency with the pixel-wise GMM to determine the background model. We first represent each pixel with a hybrid feature vector, w...
An online approach is proposed for Video registration of dynamic scenes, such as scenes with dynamic textures, moving objects, motion parallax, etc. This approach has three steps:...
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
Abstract. Current CAPTCHAs require users to solve objective questions such as text recognition or image recognition. We propose a class of CAPTCHAs based on collaborative filterin...