Jie Liu

Jie Liu (刘杰)

Ph.D. Student

University of Amsterdam

VISLAB

About

I am a fourth-year Ph.D. student supervised by Efstratios Gavves and Jan-Jakob Sonke at the University of Amsterdam. I am also a member of VISLAB and ELLIS .

My research aims to develop human-centered machines that augment human capabilities in perception, reasoning, and interaction with the world. To achieve this, I am focusing on the following topics:

Efficient Learning: few-shot segmentation, domain adaptation, prompt learning

Human-AI Interaction: interactive segmentation, multi-agent cooperation

Foundation Models: multi-modal learning, vision-language models, healthcare application

News

  • [July 2024] One paper on Interactive Segmentation was accepted in ECCV2024.
  • [June 2024] One paper on Domain Adaptation was accepted in AI Statistics 2024.
  • [Sep 2023] One work on Few-shot point cloud segmentation was accepted in 3DV2024.
  • [June 2023] One paper was accepted in ICCV2023 VCL workshop.
  • [Sep 2022] One paper was accepted to BMVC2022.
  • [June 2022] One paper wass accepted to ACM MM 2022.
  • [March 2022] One paper was accepted to CVPR 2022.
  • [Sep 2021] I joined in VISLAB as a Phd candidate.

Publications

Dynamic Transformer for Few-shot Instance Segmentation
None
Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation
None
Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation
None
Few-Shot Semantic Segmentation With Cyclic Memory Network
None

Contact