Zijie Ye

I'm a 4th-year PhD candidate at Department of Computer Science and Technology (DCST), Tsinghua University. My advisor is Prof. Jia Jia. I received my B.Eng. degree from DCST, Tsinghua University in 2020.

I am working on 3D Human Motion Generation & Processing. I am actively looking for full-time positions. Please send an email if you are interested.

Email  /  Google Scholar  /  Github

profile photo

Selected Publications

Skinned Motion Retargeting with Dense Geometric Interaction Perception
Zijie Ye, Jia-Wei Liu, Shikun Sun, Jia Jia, Mike Zheng Shou
NeurIPS Spotlight, 2024
PDF

We introduce MeshRet, a pioneering solution that facilitates geometric interaction-aware motion retargeting across varied mesh topologies in a single pass. We present the SCS and the novel DMI field to guide the training of MeshRet, effectively encapsulating both contact and non-contact interaction semantics.

Semantics2Hands: Transferring Hand Motion Semantics between Avatars
Zijie Ye, Jia Jia, Junliang Xing
ACM MM Oral, Brave New Idead Award 2023
PDF / Project Page / arXiv / Code

Given a source hand motion and a target hand model, our method can retarget realistic hand motions with high fidelity to the target while preserving intricate motion semantics.

Salient Co-Speech Gesture Synthesizing with Discrete Motion Representation
Zijie Ye, Jia Jia, Haozhe Wu, Shuo Huang, Shikun Sun, Junliang Xing
ICASSP, 2023
PDF / Code

We propose to synthesize co-speech gestures using discrete motion representation (DMR). By learning a DMR space for gesture motions and modeling the distribution of DMR, our approach generates more high-quality salient motions.

Human motion modeling with deep learning: A survey
Zijie Ye, Haozhe Wu, Jia Jia
AI Open, 2022
Paper

We present a comprehensive survey of recent human motion modeling researches with deep learning techniques.

ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit
Zijie Ye, Haozhe Wu, Jia Jia, Yaohua Bu, Wei Chen, Fanbo Meng, Yanfeng Wang
ACM MM Oral, 2020
PDF / arXiv

We propose to formalize the human choreography knowledge by defining CAU and introduce it into music-to-dance synthesis. We propose a two-stage framework ChoreoNet to implement the music-CAU-skeleton mapping. Experiments demonstrate the effectiveness of our meth

Misc

  • Gold Medal, China Chemistry Olympiad, 2015
  • Tsinghua University Freshman Scholarship, 2016
  • Excellent Undergraduate of Dept. of CST, 2020
  • 84 Innovation Scholarship of Dept. of CST, 2021

Based on Jon Barron's website.