A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials

Måns Larsson, Anurag Arnab, Fredrik Kahl, Shuai Zheng 0001, Philip H. S. Torr. A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials. In Marcello Pelillo, Edwin R. Hancock, editors, Energy Minimization Methods in Computer Vision and Pattern Recognition - 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, Revised Selected Papers. Volume 10746 of Lecture Notes in Computer Science, pages 564-579, Springer, 2017. [doi]

Authors

Måns Larsson

This author has not been identified. Look up 'Måns Larsson' in Google

Anurag Arnab

This author has not been identified. Look up 'Anurag Arnab' in Google

Fredrik Kahl

This author has not been identified. Look up 'Fredrik Kahl' in Google

Shuai Zheng 0001

This author has not been identified. Look up 'Shuai Zheng 0001' in Google

Philip H. S. Torr

This author has not been identified. Look up 'Philip H. S. Torr' in Google