Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
This paper presents a novel method for illuminationinvariant and contrast preserving feature extraction, aimed at improving performance of tracking under complex light condition. ...
We study algebraic feedback shift registers (AFSRs) based on quotients of polynomial rings in several variables over a finite field. These registers are natural generalizations o...
This paper proposes a unified framework for spatiotemporal segmentation of video sequences. A Bayesian network is presented to model the interactions among the motion vector field...
Markov random field (MRF) models, including conditional random field models, are popular in computer vision. However, in order to be computationally tractable, they are limited to ...