Cumulative attribute space regression for head pose estimation and color constancy

作者：

Highlights：

• We show that joint prediction of multiple targets can exploit the target correlation structure and lead into improved accuracy.

• We propose an approximate method for cases with more than two outputs. This prevents the combinatorial explosion.

• We study the performance for two multi-target regression cases: (a) 2D face pose estimation, (b) 3D face pose estimation and (c) three-output (RGB) illuminant estimation for color constancy.

摘要

•We show that joint prediction of multiple targets can exploit the target correlation structure and lead into improved accuracy.•We propose an approximate method for cases with more than two outputs. This prevents the combinatorial explosion.•We study the performance for two multi-target regression cases: (a) 2D face pose estimation, (b) 3D face pose estimation and (c) three-output (RGB) illuminant estimation for color constancy.

论文关键词：Multivariate regression,Cumulative attribute space,Head pose,Color constancy

论文评审过程：Received 11 April 2018, Revised 21 September 2018, Accepted 9 October 2018, Available online 10 October 2018, Version of Record 14 October 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.10.015