Commutative Lie Group VAE for Disentanglement Learning
Xinqi Zhu, Chang Xu, Dacheng Tao
International Conference on Machine Learning (Oral/Long Talk)
CV
Education
- Ph.D. in Computer Science, University of Sydney, 2022. Thesis: Learning Disentangled Representations
- B.S. in Computer Science, Shanghai Jiao Tong University, 2018. 89.04/100. Thesis: Temporal Modeling in Action Recognition (top 2%)
- Exchange student in Computer Science, University of New South Wales, 2017. 88.50/100 (full HD)
Working experience
- April 2022 - Present : Applied Scientist Intern
- Amazon IML AU
- Collaborator: Dr. Vu Nguyen and Dr. Thalaiyasingam Ajanthan
- April - July 2019 : Visiting Researcher
- University of Sydney
- Supervisor: Dr. Chang Xu and Prof. Dacheng Tao
- 2020 - 2021
- University of Sydney
- Tutor of the course Deep Learning COMP5329
Service
- Reviewer for AAAI2023, NeurIPS2021/22, ECCV2022, ICLR2022/23, CVPR2022, ICML2021, ACMMM2021, Transactions on Machine Learning Research, IEEE Transactions on Multimedia
Publications
Where and What? Examining Interpretable Disentangled Representations
Xinqi Zhu, Chang Xu, Dacheng Tao
Conference on Computer Vision and Pattern Recognition (Oral, Best Paper Candidate)Learning Disentangled Representations with Latent Variation Predictability
Xinqi Zhu, Chang Xu, Dacheng Tao
European Conference on Computer VisionApproximated Bilinear Modules for Temporal Modeling
Xinqi Zhu, Chang Xu, Langwen Hui, Cewu Lu, Dacheng Tao
International Conference on Computer VisionB-CNN: Branch Convolutional Neural Network for Hierarchical Classification
Xinqi Zhu, Michael Bain
arXiv pre-print
Skills
- PyTorch
- TensorFlow
- Python
- C++