University of Cambridge > Talks.cam > Cambridge Image Analysis Seminars > Recent Works on Continuous Multi-Label Optimization

Recent Works on Continuous Multi-Label Optimization

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Carola-Bibiane Schoenlieb.

Invited talk

In this talk my recent works on variational multi-label problems is presented. The talk is divided into two parts: The first part discusses how to utilize co-occurrence, hierarchical, proximity and label transition priors in order to improve the resulting labelling. Moreover applications in semantic image segmentation and motion segmentation of RGB -D images are presented. The second part introduces a novel approach to improving the integrality of the solution to relaxed multi-labelling problems. To this end, we incorporate the entropy of the objective variable as a measure of the relaxation tightness.

This talk is part of the Cambridge Image Analysis Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity