Feng Liu  

Ph.D. candidate

Room 260, Academy 2 Building
School of Computer Science and Technology
University of Chinese Academy of Sciences
Beijing, China, 101408.

Email: liufeng20@mails.ucas.ac.cn;
Github: https://github.com/LiewFeng;
Google Scholar: https://scholar.google.com

Biography

I am a Ph.D. candidate in LAMP (Learning And Machine Perception Laboratory) in the University of Chinese Academy of Sciences, advised by Prof. Fang Wan and Prof. Qixiang Ye. I earned a B.E. from the Harbin Institute of Technology, Shenzhen in June 2020.

I did research about 2D Object Detection and 3D Object Detection (4 paper accepted) before. I did research about Multimodal Large Language Model (1 paper under review) recently. Now I focus and Text-to-Image/Video Model.

I am expected to graduate in 2025, and I am actively looking for full-time jobs on Text-to-Image/Video Model(1st choice) or Multimodal Large Language Model(2nd choice).

Experience

Research Intern, 3D Object Detection, Megvii Inc, 2023.04-2024.01

Research Intern, Video Generation, Alibaba TongYi Vision Intelligence Lab, 2024.07-

Publications & Preprints

(* Equal Contribution)
Yuzhong Zhao*, Feng Liu*, Yue Liu, Mingxiang Liao, Chen Gong, Qixiang Ye, Fang Wan
DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution
arXiv
[Paper] [Code]
Feng Liu, Tengteng Huang, Qianjing Zhang, Haotian Yao, Chi Zhang, Fang Wan, Qixiang Ye, Yanzhao Zhou
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection
2024 European Conference on Computer Vision (ECCV 2024)
[Paper] [Code]
Feng Liu*, Xiaosong Zhang*, Zhiliang Peng, Zonghao Guo, Fang Wan, Xiangyang Ji, Qixiang Ye
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
2023 IEEE/CVF International Conference on Computer Vision (ICCV 2023)
[Paper] [Code]
Feng Liu, Xiaosong Zhang, Fang Wan, Xiangyang Ji, Qixiang Ye
Domain Contrast for Domain Adaptive Object Detection
2021 IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT 2021)
[Paper] [Code]
Bohao Li, Boyu Yang, Chang Liu, Feng Liu, Rongrong Ji, Qixiang Ye
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
[Paper] [Code]


Statistics