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...
Many vision tasks such as scene segmentation, or the recognition of materials within a scene, become considerably easier when it is possible to measure the spectral reflectance o...
Jong-Il Park, Moon-Hyun Lee, Michael D. Grossberg,...
Computer-vision attention processes allocate computational resources to different parts of visual input and can lead to faster object recognition and image analysis. This paper p...
We present a wide-baseline image matching approach
based on line segments. Line segments are clustered into
local groups according to spatial proximity. Each group is
treated as...
We present a pattern recognizer to classify a variety of objects and their pose on a table from real world images. Learning of weights in a linear discriminant is based on estimat...