A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
The last 20 years have seen an increasing number of computer vision tasks being formulated as energy optimization problems. Such energy-based modeling can integrate multiple image cues and priors, thus making visual processing robust to noise and resilient to some degree of model misspecification. The scale of the resulting optimization problems however often posits them beyond the reach of generic optimization techniques and solvers. This motivates two active research directions, namelydoi:10.1007/s11263-013-0637-9 fatcat:cohoj4cw7ra7lmbyzvklwzdwyi