Learn More
Deep learning based methods have achieved unprecedented success in solving several computer vision problems involving RGB images. However, this level of success is yet to be seen on RGB-D images owing to two major challenges in this domain: training data deficiency and multi-modality input dissimilarity. We present an RGB-D object recognition framework that(More)
Existing RGB-D object recognition methods either use channel specific handcrafted features, or learn features with deep networks. The former lack representation ability while the latter require large amounts of training data and learning time. In real-time robotics applications involving RGB-D sensors, we do not have the luxury of both. In this paper, we(More)
3D object categorization is a non-trivial task in computer vision encompassing many real-world applications. We pose the problem of categorizing 3D polygon meshes as learning appearance evolution from multi-view 2D images. Given a corpus of 3D polygon meshes, we first render the corresponding RGB and depth images from multiple viewpoints on a uniform(More)
First-person videos have unique characteristics such as heavy egocentric motion, strong preceding events, salient transitional activities and post-event impacts. Action recognition methods designed for third person videos may not optimally represent actions captured by first-person videos. We propose a method to represent the high level dynamics of(More)
The intestine displays an architecture of repetitive crypt structures consisting of different types of epithelial cells, lamina propia containing immune cells, and stroma. All of these heterogeneous cells contribute to intestinal homeostasis and participate in antimicrobial host defense. Therefore, identifying a surrogate model for studying immune response(More)
  • 1