A deep coarse-to-fine network for head pose estimation from synthetic data

Y Wang, W Liang, J Shen, Y Jia, LF Yu - Pattern Recognition, 2019 - Elsevier
Various applications of human-computer interaction are based on the estimation of head
pose, which is challenging due to different facial appearance, inhomogeneous illumination …

[PDF][PDF] Contrastive Graph Transformer Network for Personality Detection.

Y Zhu, L Hu, X Ge, W Peng, B Wu - IJCAI, 2022 - academia.edu
Personality detection is to identify the personality traits underlying social media posts. Most
of the existing work is mainly devoted to learning the representations of posts based on …

Comic-guided speech synthesis

Y Wang, W Wang, W Liang, LF Yu - ACM Transactions on Graphics …, 2019 - dl.acm.org
We introduce a novel approach for synthesizing realistic speeches for comics. Using a comic
page as input, our approach synthesizes speeches for each comic character following the …

Towards accurate facial motion retargeting with identity-consistent and expression-exclusive constraints

L Mo, H Li, C Zou, Y Zhang, M Yang, Y Yang… - Proceedings of the AAAI …, 2022 - ojs.aaai.org
We address the problem of facial motion retargeting that aims to transfer facial motion from a
2D face image to 3D characters. Existing methods often formulate this problem as a 3D face …

Personality perception in human videos altered by motion transfer networks

A Yurtoğlu, S Sonlu, Y Doğan, U Güdükbay - Computers & Graphics, 2024 - Elsevier
The successful portrayal of personality in digital characters improves communication and
immersion. Current research focuses on expressing personality through modifying …

Photo stand-out: Photography with virtual character

Y Wang, S Hou, B Ning, W Liang - Proceedings of the 28th ACM …, 2020 - dl.acm.org
In this paper, we propose a novel optimization framework to synthesize an aesthetic pose for
the virtual character with respect to the presented user's pose. Our approach applies …