Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that ar...
Michael J. Black, Yaser Yacoob, Allan D. Jepson, D...
Abstract-- This paper describes two distortion estimation techniques for object recognition that solve EZ-Gimpy and Gimpy-r, two of the visual CAPTCHAs ("Completely Automated ...
Gabriel Moy, Nathan Jones, Curt Harkless, Randall ...
We observe that everyday images contain dozens of objects, and that humans, in describing these images, give different priority to these objects. We argue that a goal of visual rec...
Optical flow in monocular video can serve as a key for recognizing and tracking the three-dimensional pose of human subjects. In comparison with prior work using silhouettes as a ...