Interpretable Machine Learning

Inspired by Human Vision/Behavior and Psycho-physics, we are developing computational models to achieve superior performance in Time-series Prediction, Recommendation Systems, etc.

Image
Processing

We have deveoped lightweight neural network technologies for low-level image and video processing tasks, including resampling, denosing, enhancement, etc.

Video
Compression

We are working on AI based image and video compression, and have contributed to various video coding standards, including H.266/VVC, JPEG-AI, VCM, IEEE 1857.11, etc.

AI Generated Content

We have developed various technologies for AI Generated Content (AIGC), including Text-Image-to-Video Generation, Image-Video-to-Text Generation, etc.

Computer
Vision

We are working on deep learning technologies for computer vision, including visual relation detection, representation learning, Neural Radiance Field (NeRF), etc.

Research Projects

Since the establishment in 2013, we have received various funding supports from MOE, MOST, NSFC, and industrial partners.

Read More

Open to collaborations



Please contact: zzchenATwhu.edu.cn