4 papers
Application-Driven AI Paradigm for Human Action Recognition
Zezhou Chen, Yajie Cui, Kaikai Zhao +2
Human action recognition in computer vision has been widely studied in recent years. However, most algorithms consider only certain action specially with even high computational co…
A Neural Virtual Anchor Synthesizer based on Seq2Seq and GAN Models
Zipeng Wang, Zhaoxiang Liu, Zezhou Chen +2
This paper presents a novel framework to generate realistic face video of an anchor, who is reading certain news. This task is also known as Virtual Anchor. Given some paragraphs o…
A Realistic Face-to-Face Conversation System based on Deep Neural Networks
Zezhou Chen, Zhaoxiang Liu, Huan Hu +4
To improve the experiences of face-to-face conversation with avatar, this paper presents a novel conversation system. It is composed of two sequence-to-sequence models respectively…
Facial Pose Estimation by Deep Learning from Label Distributions
Zhaoxiang Liu, Zezhou Chen, Jinqiang Bai +2
Facial pose estimation has gained a lot of attentions in many practical applications, such as human-robot interaction, gaze estimation and driver monitoring. Meanwhile, end-to-end…