Scholar
Haiyi Mei
Google Scholar ID: TOZ9wR4AAAAJ
SenseTime Research
Citations & Impact
Citations
528
H-index
9
i10-index
9
Publications
18
Co-authors
14
list available
Resume (English only)
Academic Achievements
- Published multiple papers in top-tier conferences such as ECCV 2024, CVPR 2024, NIPS 2023, and ICCV 2023. Filed a patent CN113011334A.
Research Experience
- Mid-Level Algorithm Researcher at SenseTime, responsible for text/image-to-video generation projects, successfully reproducing results comparable to CogVideo VAE. Contributed to the data annotation process to ensure high-quality video datasets. Developed automated solutions for video content acquisition from various online platforms. Led the development of XRFeitoria, a rendering toolbox for synthetic data generation, and published several papers. Designed SynBody, a large-scale synthetic dataset, and participated in the design of SMPL-XL, building a SaaS platform.
Background
- A committed algorithm researcher and backend engineer with 3 years of industry experience. Specializing in 3D synthetic data generation for computer vision tasks, contributed to 9 papers in top-tier conferences. Well-versed in the text-to-video generation pipeline, including VAE training, dataset preparation, automated annotation, and video acquisition. Passionate about developing autonomous AI agents, leveraging backend expertise and cutting-edge LLMs to create intelligent, scalable solutions.
Miscellany
- Proficient in Python, C++, Blender, Unreal Engine, and other tools.
