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

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Recent Works on Continuous Multi-Label Optimization

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 8980.17857143 kWh Hybrid - Maxwell Centre & on Zoom Live on Zoom, pre-registration essential here: bit.ly/349mHZG

Other talks

"Gods, Monsters & Middle-class Uncles: Indian Comics in a Time between Worlds" Classical Reductions and Converse Bounds in Quantum Hypothesis Testing Cultural evolution creates language-like structure: from humans to humpback whales and beyond There is no such thing as weather: a historical and cultural geography of weather (and health) Title to be confirmed Coming soon
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity