Related Experiment Video
Updated: Jul 19, 2026

08:25
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
Published on: May 7, 2019
Iterative local-global energy minimization for automatic extraction of objects of interest
Gang Hua1, Zicheng Liu, Zhengyou Zhang
1Microsoft Live Labs, One Microsoft Way, Redmond, WA 98052, USA. ganghua@microsoft.com
IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 22, 2006
Abstract:
We propose a novel global-local variational energy to automatically extract objects of interest from images. Previous formulations only incorporate local region potentials, which are sensitive to incorrectly classified pixels during iteration. We introduce a global likelihood potential to achieve better estimation of the foreground and background models and, thus, better extraction results. Extensive experiments demonstrate its efficacy.
