Scholar
Zhongdao Wang
Google Scholar ID: VkKYpHIAAAAJ
Noah's Ark Lab, Huawei
Citations & Impact
Citations
5,165
H-index
19
i10-index
22
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Selected Publications: 'PIXART-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis' (ICLR 2024); 'PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation' (ECCV 2024); 'Towards Real-time Multi-Object Tracking' (ECCV 2020); 'Do Different Tracking Tasks Require Different Appearance Models?' (NeurIPS 2021).
Research Experience
- Currently a researcher at Noah's Ark Lab, Huawei. During his Ph.D., he was involved in several research projects, including JDE, UniTrack, CycAs series, Circle Loss, and D-Softmax Loss.
Education
- Ph.D. in Electronic Engineering from Tsinghua University, supervised by Prof. Liang Zheng, Dr. Yifan Sun, Dr. Luca Bertinetto, and Prof. Hengshuang Zhao; B.S. in Physics from Tsinghua University
Background
- Research Interests: In the long term, developing general embodied intelligent agents (e.g., autonomous driving cars). Believes that the emergence of general machine intelligence requires observing, interacting with, and learning from the physical world. In the short term, focuses on perception algorithms for autonomous driving, including 2D/3D object detection, segmentation, tracking, 3D reconstruction, and offboard perception (for auto-labeling). Previously, worked on representation learning and object tracking.
Miscellany
- Personal interests not mentioned
