Sorry, you need to enable JavaScript to visit this website.

Deep Regression Forest with Soft-Attention for Head Pose Estimation

Primary tabs

Citation Author(s):
Xiangtian Ma, Nan Sang, Xupeng Wang, Shihua Xiao
Submitted by:
Xiangtian Ma
Last updated:
3 November 2020 - 9:48am
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters Name:
Xiangtian Ma

Abstract 

Abstract: 

The task of head pose estimation from a single depth image is challenging, due to the presence of large pose variations, occlusions and inhomegeneous facial feature space. To solve the problem, we propose Deep Regression Forest with Soft-Attention (SA-DRF) in a multi-task learning setup. It can be integrated with a general feature learning net and jointly learned in an end-to-end manner. The soft-attention module is facilitated to learn soft masks from the general features and feeds the forest with task-specific features to regress head poses. Experiments on the Biwi Head Pose and Pandora datasets demonstrate its superior performance compared to current state-of-the-arts.

up
0 users have voted:

Dataset Files

ICIP2020_paper2985_slides.pptx

(81)