Zheyuan (David) Liu

Zheyuan (David) Liu

PhD Candidate, Deep Learning

Australian National University

Acton, Canberra



I am a PhD at the Australian National University, supervised by Prof. Stephen Gould and working with Dr. Damien Teney (Idiap Research Institute | AIML). My research focuses on multi-modal learning, primarily, vision-and-language.



Interests
  • Composed Image Retrieval
  • Vision-and-Language
  • Semantic Segmentation
  • Weakly-supervised Learning
Education

  • PhD in Deep Learning, Computer Science, 2019-2024

    Australian National University

  • Bachelor of Engineering Hons (R&D), Electronics and Communication Systems, 2015-2018

    Australian National University

Recent research

Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
Transactions on Machine Learning Research (TMLR)
Zheyuan (David) Liu, Weixuan Sun, Damien Teney, Stephen Gould
Cite Code OpenReview arXiv
Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
Bi-Directional Training for Composed Image Retrieval via Text Prompt Learning
In IEEE/CVF Winter Conference on Applications of Computer Vision 2024
Zheyuan (David) Liu, Weixuan Sun, Yicong Hong, Damien Teney, Stephen Gould
Cite Code CVF Open Access arXiv
Bi-Directional Training for Composed Image Retrieval via Text Prompt Learning
Image retrieval on real-life images with pre-trained vision-and-language models
In IEEE/CVF International Conference on Computer Vision 2021
Zheyuan (David) Liu, Cristian Rodriguez-Opazo, Damien Teney, Stephen Gould
Cite Code & Dataset CVF Open Access arXiv
Image retrieval on real-life images with pre-trained vision-and-language models