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...
This paper presents a novel approach for labeling objects based on multiple spatially-registered images of a scene. We argue that such a multi-view labeling approach is a better fi...
Scott Helmer, David Meger, Marius Muja, James J. L...
Abstract. We propose a novel method for recognition of structured images and demonstrate it on detection of windows in facade images. Given an ability to obtain local low-level dat...
Abstract. We propose a new imaging method called hemispherical confocal imaging to clearly visualize a particular depth in a 3-D scene. The key optical component is a turtleback re...
Yasuhiro Mukaigawa, Seiichi Tagawa, Jaewon Kim, Ra...
Abstract. We propose a methodology for recognizing actions at a distance by watching the human poses and deriving descriptors that capture the motion patterns of the poses. Human p...