Research Fields

• Image and Video Processing

• Machine Learning

• Pattern Recognition

• Robotic Tasks

  

Representative Researches

Image Analysis General Tasks

    >>> Low-level Vision: Derain (ACMMM2024, ICLR2024, TIP2023, ICASSP2021, ICME2020*2, ACMMM2019, ICME2019)

               

             [1] Rainmer: Learning multi-view representations for comprehensive image deraining and beyond.

            Wu Ran, Peirong Ma, Zhiquan He, Hong Lu.
               ACM International Conference on Multimedia, 2024         

                        

 

              [2] Harnessing joint rain-/detail-aware representations to eliminate intricate rains.

               Wu Ran, Peirong Ma, Zhiquan He, Hao Ren, Hong Lu.
               International Conference on Learning Representations, 2024

                                                                                                             

               [3] TRNR：Task-Driven Image Rain and Noise Removal with a Few Images Based on Patch Analysis.

               Wu Ran, Bohong Yang, Peirong Ma, Hong Lu.
               IEEE Transactions on Image Processing, 2023

                                                                                                              

               [4] Single Image Deraining via Recurrent Hierarchy Enhancement Network.
               Youzhao Yang, Hong Lu.
               ACM International Conference on MultiMedia (ACMMM),   France, Nice, Oct. 2019

                                                                                                              

    >>> Low-level Vision: Low-Light Image Enhancement (TOMM2024, TCSVT2024)

              [1] Low-Light Image Enhancement with Multi-scale Attention and Frequency-domain Optimization. 

               Zhiquan He, Wu Ran, Shulin Liu, Kehua Li, Jiawen Lu, Changyong Xie, Yong Liu, Hong Lu.
               IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024

                                                     

               

              [2] Real-Time Attentive Dilated U-Net for Extremely Dark Image Enhancement.

               Junjian Huang, Hao Ren, Shulin Liu, Yong Liu, Chuanlu Lv, Jiawen Lu, Changyong Xie, Hong Lu.

               ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2024       

                                                       

    >>> Zero-shot Learning (TCSVT2023, ICME2022)

               [1] A Transferable Generative Framework for Multi-label Generative Zero-Shot Learning.

               Peirong Ma, Zhiquan He, Wu Ran, Hong Lu.
               IEEE Transactions on Circuits and Systems for Video Techonlogy, 2023  

                                                                                                     

               [2] Semantic-Related Feature Generation for Generalized Zero-Shot Learning.

               Peirong Ma, Wu Ran, Hong Lu.
               IEEE International Conference on Multimedia and Expo (ICME),  Taiwan, Jul. 2022

                                                                                                       

    >>> Image Retrieval (TCSVT2023, ICMR2019)

          [1] ACNet: Approaching-and-Centrilizing Network for Zero-Shot Skecth-Base Image Retrieval.

             Hao Ren, Ziqiang Zheng, Yang Wu, Hong Lu, Yang Yang, Ying Shan, Sai-Kit Yeung.
             IEEE Transactions on Circuits and Systems for Video Technology, 2023

                                                                                                        

                [2] Weakly Supervised Image Retrieval via Coarse-scale Feature Fusion and Multi-level Attention Blocks.

                Xinyao Nie, Hong Lu, Zijian Wang, Jingyuan Liu, Zehua Guo.
                ACM International Conference on Multimedial Retrieval (ICMR), 2019

                                                                                                      

  >>>  Segmentation (TITS2024, TIV2023，ACMMM2023，ECAI2023)

           [1] Subclassified Loss: Rethinking Data Imblance from Subclass Perspective for Semantic Segmentation.
           Shoumeng Qiu, Xianhui Cheng, Hong Lu, Haiqiang Zhang, Ru Wan, Xiangyang Xue, Jian Pu.
             IEEE Trasctions onf Intelligent Vehicles, 2023    

          

          [2] Leveraging Smooth Deformmation Augmentation for LiDAR Point Cloud Semantic Segmentation.

           Shoumeng Qiu, Jie Chen, Chenghan Lai, Hong Lu, Xiangyang Xue, Jian Pu.
             IEEE Trasctions onf Intelligent Vehicles, 2024

          [3] SimuFlow: Simultaneously Extracting Features and Identifying Target for Unsupervised Video Object Segmentation.

           Lingyi Hong, Wei Zhang, Shuyong Gao, Hong Lu, Wenqiang Zhang.
             ACM International Conference on Multimedia (ACMMM), 2023                                

           

           [4] Intance-aware Diffusion Implicit Process for Box-based Instance Segmentation.

           Hao Ren, Xingsong Liu, Junjian Huang, Ru Wan, Jian Pu, Hong Lu.
             European Conference on Artificial Intelligence (ECAI), 2023                                

>>>  HD-Map Construction (ICASSP2024)

          [1]  Buffered Gaussian Modeling for Vectorized HD Map Construction.

            Anqi Shi, Huaqiu Chen, Hong Lu, Rui Zhang.

           IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024                                

  >>> Other Perception Tasks (ICME2023)

            [1] GSFormer: Geometric-Spatial Transformer on Point Cloud Completion.

           Yijun Long, Zhaoyu Chen, Hong Lu, Wenqiang Zhang.
             IEEE International Conference on Multimedia and Expo (ICME), 2023

>>> Pulse Localization in TCM Diagnosis (ICIP2022, ISCAS2022, ACMMMAsia2020)

         [1] 3DCNN-BASED Palpation Localization with Temporal Attention Module

         Guanhao Huang, Hong Lu, Xing Zhu, Jingjing Luo

           IEEE International Conference on Immage Processing (ICIP), 2022

          [2] SFCN: Fully Convolutional Networks for Pulse Localization

          Bohong Yang, Kai Meng, Hong Lu, Xing Zhu, Jingjing Luo

            IEEE International Symposiumm on Circuits and Systems (ISCAS), 2022

          [3] Pulse Localization Networks with Infrared Camera

          Bohong Yang, Kai Meng, Hong Lu, Xinyao Nie, Guanhao Huang, Jingjing Luo, Xing Zhu

            ACM International Conference on Multimedia in Asia (ACMMMAsia), 2020

 >>> Fashion Analysis (ECCVW2018)

          [1] Deep Fashion Analysis with Feature Map Upsampling and Landmark-driven Attention.
             Jingyuan Liu, Hong Lu.
             Workshop of European Conference on Computer Vision (ECCVW), Germen, Munich, Sep.2018

                                                                                                

 

Visual Action Recognition and Object Tracking

     >>> Weakly-supervised Temporal Action Localization (ICME2023)

            [1] Weakly-supervised Temporal Action Localization with Adaptive Clustering and Refining Network.

               Hao Ren, Wu Ran, Xingsong Liu, Haoran Ren, Hong Lu, Rui Zhang, Cheng Jin.
              IEEE International Conference on Multimedia and Expo (ICME), 2023.

                                                

     >>> Action Recognition (ISCAS2022, ICASSP2021)

           [1] RARN: A Real-time Skeleton-based Action Recognition Network for Auxiliary Rehabilitation

             Mengqi Shen, Hong Lu

                IEEE International Symposiumm on Circuits and Systems (ISCAS), 2022

                

               [2] Multi-directional Convolution Networks with Spatial-Temporal Feature Pyramid Module for Action Recognition
hh         Bohong Yang, Zijian Wang, Wu Ran, Hong Lu, Yi-Ping Phoebe Chen
hh         IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), June 2021

                                                                                         

    >>> Teaching Video Analysis (PRL2020, ICMR2015)

           [1] In-classroom Learning Analytics Based on Student Behavior, Topic and Teaching Characteristic Mining
hh         Bohong Yang, Zeping Yao, Hong Lu, Yaqian Zhou, Jinkai Xu
hh        Pattern Recognition Letter, vol. 129, pp. 224-231, 2020

                                                                                                                                                          

     

Simultaneous Localization and Mapping (SLAM) of Robotics (TITS2024, TMM2022)

          [1]  VPL-SLAM: A Vertical  Line Supported Point Line Monocular SLAM System

           Qi Chen, Yu Cao, Jaiwei Hou, Shoumeng Qiu, Bo Chen, Xiangyang Xue, Hong Lu, Jian Pu
              IEEE Transactions on Intelligent Transportation Systems (TITS), 2024

                                                   

             [2] Multi-Classes and Motion Properties for Concurrent Visual SLAM in Dynamic Environments

               Bohong Yang, Wu Ran, Lin Wang, Hong Lu, Yi-Ping Phoebe Chen
hh         IEEE Transactions on Multimedia (TMM), 2022

                                                                                                                              

Reinforcement Learning (RL) for Navigation of Robotics

     >>> RL in the Game of Go (TG2020)

                [1] Learning the Game of Go by Scalable Network Without Prior Knowledge of Komi
hh           Bohong Yang, Lin Wang, Hong Lu, Youzhao Yang
hh           IEEE Transactions on Games, 2020  

                                     

     >>> RL Exploration (ICPCSEE2018)

           [1] A Novel Experience-based Exploration Method for Q-Learning

               Bohong Yang, Hong Lu, Baogen Li, Zheng Zhang, Wenqiang Zhang

                International Conference of Pioneering Computer Scientists, Engineering and Educators (ICPCSEE), China, Zhengzhou, Sep. 2018