RESEARCH INTERESTS:
My research interests mainly include Multimedia Computing, Computer Vision and Pattern Recognition. I am particularly interested in the following topics:
Current topics:
(1) Autonomous and Controllable Large Models in Smart Education, including Smart Problem-Solving and Question Generation, Handwritten Answer Sheet Recognition, Digital Human Teaching and Topic Explanation, Automatic Data Annotation, and Automatic Grading of Subjective Questions (e.g., fill-in-the-blank and writing tasks) for various subjects.
(2) Robust Vision Perception in Adverse Conditions: 1) Degraded Image Restoration and Enhancement: New Deep Architectures and Models for Degraded Image/Video Restoration (e.g., denoising, deraining, deblurring and dehazing), Low-Light Image Enhancement, and High-Level Task Driven Low-Level Vision; 2) Autonomous Driving Perception: BEV/OCC Prediction and Perception, High-Quality and Generalizable Autonomous Driving Data Generation, Lightweight Deployment and Real-Time Inference of Autonomous Driving Models.
(3) Image/Video Generation, Digital Human and Deepfake Detection: New Deep Architectures and Models for Text-to-Image/Video Generation, Image-to-Video Generation, Automatic PPT Generation, Deepfake Detection, and Emotional Digital Human.
(4) Model Compression and Deployment of DNNs: New Network Quantization Methods or Lightweight Architectures for High-level and Low-level Vision Tasks, with deployment on resource limited edge devices (e.g., mobile devices, robot vision and visual imaging system).
Previous topics (Discontinued):
(5) Deep Degraded Image Restoration and Enhancement: New Deep Architectures and Models for Degraded Image/Video Restoration (e.g., denoising, deraining, deblurring and dehazing), Low-Light Image Enhancement, and High-Level Task Driven Low-Level Vision, with emerging applications (e.g., autonomous driving, visual imaging systems, video surveillance and robot vision) in complex environments.
(6) Low-Dimensional Modeling of High-Dimensional Data: Sparse Dictionary Learning, Low-Rank Coding, Concept Factorization, Manifold Learning, and Their Deep/Multilayer Extensions, for feature learning and extraction.
(7) Semi-Supervised Classifier Modeling: Graph based Novel Label Propagation Algorithms, and Deep Semi-Supervised Learning, with application to image annotation and classification.
PROJECT & FUNDING:
AWARD & HONOR:
COLLABORATORS:
Prof. Shuicheng Yan ( Sea AI Lab, Singapore; National University of Singapore; ACM/AAAI/IEEE/IAPR Fellow, Fellow of Singapore Academy of Engineering)
Prof. Cheng-Lin Liu (Chinese Academy of Sciences; IEEE/IAPR Fellow)
Prof. Tommy W.S. Chow (City University of Hong Kong; IEEE Fellow)
Prof. Meng Wang (Hefei University of Technology, China; IEEE/IAPR Fellow)
Prof. Richang Hong (Hefei University of Technology, China)
Prof. Yi Yang (Zhejiang University, China; University of Technology Sydney, Australia)
Prof. Mingliang Xu (Zhengzhou University, China)
Prof. Guangcan Liu (School of Automation, Southeast University, China)
Dr. Sheng Li (School of Data Science, University of Virginia, USA)
Dr. Xiaojie Jin (Bytedance Research, USA)
Prof. Haijun Zhang (Harbin Institute of Technology, Shenzhen, China)
Prof. Mingbo Zhao (Donghua University, Shanghai, China)
Dr. Jicong Fan (The Chinese University of Hong Kong, Shenzhen, China)
RESOURCE LINKS:
Machine Learning & AI Journal Rankings (by Guide2Research)
Machine Learning & AI Conference Rankings (by Guide2Research)
Papers With Code: The Latest Papers in Machine Learning and Computer Vision
Reproducible Research in Computational Science: Papers and Codes
Digital Library, CS Journal & Conference List from LAMDA at Nanjing University