Scholar
Xianzheng Ma
Google Scholar ID: NS8g2mMAAAAJ
VGG & AVL, University of Oxford
Citations & Impact
Citations
1,233
H-index
15
i10-index
19
Publications
20
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Paper accepted to CVPR 2025; submitted a survey and meta-analysis paper on 3D tasks empowered by multimodal large language models to TPAMI; proposed a 3D multimodal model for general 3D learning, Point-Bind, and the first 3D large language model, Point-LLM; proposed a two-stage framework, CapeFormer, for category-agnostic pose estimation; offered an alternative and new solution for continual test-time adaptation with Decorate the Newcomers; alleviated the domain gap caused by mixed fog influence and style variation without labels in Both Style and Fog Matter; proposed a reinforced motion transformation network, REMOTE, for semi-supervised 2D pose estimation in videos.
Research Experience
- Currently a member of both the Visual Geometry Group and Active Vision Group at the University of Oxford; previously a full-time researcher at Shanghai AI Lab, under the supervision of Prof. Chao Dong.
Education
- Obtained Bachelor's and Master's degrees from Wuhan University in 2018 and 2021; currently a DPhil student at the Department of Engineering Science, University of Oxford, since October 2023, supervised by Prof. Victor Prisacariu and Prof. Iro Laina.
Background
- Research interests include LLMs, 3D computer vision, and robotics, especially using LLMs' world knowledge to enhance 3D world understanding and interaction.
