Da Chen

Staff

Department of Computer Science

Dr Da Chen

I am currently a Lecturer in the Department of Computer Science at the University of Bath. Prior to this, I was a Postdoc researcher in a joint project between Alibaba Group and The Institute of Automation, Chinese Academy of Sciences.

My research focuses on computer vision, machine learning, multimodal learning, and related areas. I am particularly interested in solving complex practical tasks under “limited” data conditions, such as learning with limited labelled data, out-of-distribution data, cross-domain learning, incremental learning, etc. To this end, I have proposed multiple solutions for few-shot learning image classification, out-of-distribution detection, and other tasks. I am also interested in video-related computer vision and multimodal learning tasks such as video summarization, video object detection, dense video captioning, etc.

Research interests:

Computer vision, deep learning, multimodal learning: general CV/ML tasks in practical scenarios.
Learning with limited data: Learning with imbalanced data, long-tailed data, open-set data, out-of-distribution data, etc; incremental learning, few-shot learning, etc.
Video processing: multimodal learning with video with visual, textual, and audio information.

University of Bath Research Portal:

https://researchportal.bath.ac.uk/en/persons/chen-chen-2

Second Supervisors

Wenbin Li

Department of Computer Science

Research interests:

Reinforcement learning and its inverse problems;
Graph and network optimisation;
Continuous state approximation.

learn more

Georgios Exarchakis

Department of Computer Science

Research interests:

Learning Invariant Representations of High Dimensional Data
Efficient Inference and Learning in Probabilistic Models
Deep Learning

learn more

Rohit Babbar

Department of Computer Science

Research interests:

supervised learning problems with large label spaces,
learning with long-tailed data, and under label/input noise,
sparse neural networks for energy & memory efficient training/fine-tuning with LLMs, and
generalisation/robustness in deep learning.

learn more