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...
In this work, we propose a contour and region detector for video data that exploits motion cues and distinguishes occlusion boundaries from internal boundaries based on optical ï¬...
Patrik Sundberg, Jitendra Malik, Michael Maire, Pa...
We present a markerless motion capture approach that reconstructs the skeletal motion and detailed time-varying surface geometry of two closely interacting people from multi-view ...
The task of 2-D articulated human pose estimation in natural images is extremely challenging due to the high level of variation in human appearance. These variations arise from di...
We introduce a robust estimator called generalized projection based M-estimator (gpbM) which does not require the user to specify any scale parameters. For multiple inlier structu...
We present a novel algorithm for automatically applying constrainable, L1-optimal camera paths to generate stabilized videos by removing undesired motions. Our goal is to compute ...
Unsupervised categorization of objects is a fundamental problem in computer vision. While appearance-based methods have become popular recently, other important cues like function...