Guangwei (Gavin) Gao (高广谓)

Intelligent Visual Information Perception Laboratory (IVIPLab)


Guangwei Gao (IEEE Senior Member)

Associate Professor
Institute of Advanced Technology
Nanjing University of Posts and Telecommunications
No.9, Wenyuan Road, Xianlin, Nanjing, China, 210046

E-mail: (commonly used) &
[Personal Github] [Group Github] [Google Scholar] [DBLP]

Genius only means hard-working all one's life .—— Mendeleyer , Russian Chemist

Brief Biography

    Guangwei Gao received his B.S. degree from Nanjing Normal University in 2009, and received the Ph.D. degree in pattern recognition and intelligence systems from the Nanjing University of Science and Technology in 2014. He was a Visiting Student at the Department of Computing, The Hong Kong Polytechnic University, in 2011 and 2013, respectively. From 2019 to 2021, he was also a Project Researcher with the National Institute of Informatics, Japan. He is currently an Associate Professor in Nanjing University of Posts and Telecommunications. His research interests include pattern recognition and computer vision. He has published more than 70 scientific papers in IEEE/ACM/AAAI venues, including IEEE TIP/TCSVT/TITS/TMM/TIFS, ACM TOIT/TOMM, AAAI, IJCAI, PR, etc, and served as a reviewer for journals and conferences including IEEE TPAMI/TMM/TCSVT/TNNLS/TYCB, CVPR, ICCV, ECCV, AAAI, etc. He is also an IEEE Senior Member and CCF Senior Member.

Research Interests

    My research interests lie in machine learning, pattern recognition, and learning-based vision problems. Particularly, I'm interested in heterogeneous image analysis (recognition, super-resolution), lightweight deep neural network design (used for semantic segmentation, super-resolution), analysis and processing of cross-modality visual data (person re-identification).

Recent News

  • [11/2022] Our paper "Occluded Visible-infrared Person Re-identification" was accepted by IEEE Transactions on Multimedia (CCF B)

  • [11/2022] Our paper "Semi-supervised Cross-modal Hashing Via Modality-specific and Cross-modal Graph Convolutional Networks" was accepted by Pattern Recognition (CCF B)

  • [10/2022] Our paper "Lightweight Feature De-Redundancy and Self-Calibration Network for Efficient Image Super-Resolution" was accepted by ACM TOMM (CCF B)

  • [09/2022] CFP for Special Session "Representation Learning for Computer Vision and Pattern Recognition" at the Journal of Mathematics, Deadline: March 31, 2023

  • [08/2022] I will serve as a PC Member for AAAI 2023

  • [07/2022] Our paper "Multi-feature Sparse Similar Representation for Person Identification" was accepted by Pattern Recognition (CCF B)

  • [07/2022] Our paper "Context-Patch Representation Learning with Adaptive Neighbor Embedding For Robust Face Image SuperResolution" was accepted by IEEE TMM (CCF B)

  • [07/2022] I will serve as a Session Chair for ICME 2022

  • [06/2022] I was elevated to the grade of IEEE Senior Member

  • [06/2022] I will serve as a PC Member for BigMM 2022

  • [05/2022] Our paper "Cross-Resolution Person Re-Identification via Deep Group-Aware Representation Learning" was accepted by ICPR'22 (CCF C)

  • [05/2022] CFP for Special Session "Image Processing and Analysis for Object Detection" at the Journal of Sensors, Deadline: October 1, 2022

  • [04/2022] CFP for Special Session "Visual Transformer for Image/Video Understanding (VSI-vti)" at the Journal of Computers & Electrical Engineering, Deadline: July 1, 2022

  • [04/2022] I will serve as a PC Member for CCBR 2022

  • [04/2022] Our paper "Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformer" was accepted by IJCAI'22 (CCF A), with the acceptance rate to be 15%

  • [04/2022] Our paper "Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation" was accepted by NTIRE at CVPR'22

  • [03/2022] Our paper "FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation" was accepted by IEEE TMM (CCF B)

  • [01/2022] Our paper "Leaning Compact and Representative Features for Cross-Modality Person Re-Identification" was accepted by World Wide Web (WWW) (CCF B)

  • [12/2021] Our paper "Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution" was accepted by AAAI'22 (CCF A)

  • [08/2021] Our paper "JSPNet: Learning Joint Semantic & Instance Segmentation of Point Clouds via Feature Self-similarity and Cross-task Probability" was accepted by Pattern Recognition (CCF B)

  • [07/2021] Our paper "MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation" was accepted by IEEE TITS (CCF B)

  • [03/2021] Our paper "Lightweight Image Super-Resolution with Multi-scale Feature Interaction Network" was accepted by ICME'21 (CCF B)

  • [02/2021] Our paper "Graph regularized Bayesian tensor factorization based on Kronecker-Decomposable dictionary" was accepted by Computers and Electrical Engineering

  • [01/2021] Our paper "Short-term load forecasting based on improved GEP and abnormal load recognition" was accepted by ACM TOIT (CCF B)

  • [11/2020] Our paper "Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition" was accepted by IEEE TCSVT (CCF B)

  • [10/2020] Our special session titled "Advanced Representation Learning for Robust Multimedia Image Understanding" got accepted at ICME 2021, with Prof. Junjun Jiang, Prof. Licheng Liu, Prof. Tao Lu, and Prof. Jingang Shi

  • [09/2020] Our paper "Adaptive Deformable Convolutional Network" was accepted by Neurocomputing

  • [09/2020] Our paper "Chinese Image Captioning via Fuzzy Attention-based DenseNet-BiLSTM" was accepted by ACM TOMM (CCF B)

  • [08/2020] Our paper "Robust Facial Image Super-Resolution by Kernel Locality-Constrained Coupled-Layer Regression" was accepted by ACM TOIT (CCF B)

  • [08/2020] Our paper "Cross-resolution face recognition with pose variations via multilayer locality-constrained structural orthogonal procrustes regression" was accepted by Information Sciences (CCF B)

  • [07/2020] Our paper "Constructing multilayer locality-constrained matrix regression framework for noise robust face super-resolution" was accepted by Pattern Recognition (CCF B)

  • [02/2020] Our paper "Multi-scale patch based representation feature learning for low-resolution face recognition" was accepted by Applied Soft Computing


Prof. Jian Yang       Prof. Guo-Jun Qi       Prof. Yi Yu       Prof. Meng Yang       Prof. Huimin Lu       Prof. Jiantao Zhou       Dr. Juncheng Li      



Acess Count