Liu Wenxi
Professor, College of Computer and Data Science, Fuzhou University
About Me
Wenxi Liu is currently a Professor at College of Computer and Data Science, Fuzhou University, China. He currently serves as the dean of the Computer Science department. His research interests lie in the computer vision applications on crowd analysis and image understanding. He served as the visiting research associate at the Univeristy of Hong Kong, working with Prof. Wenping Wang and Prof. Jia Pan. He earned the Ph.D. degree from Computer Science Department at City University of Hong Kong in 2014, under the co-supervision of Prof. Rynson W.H. Lau and Prof. Dinesh Manocha. During his PhD, he visited the GAMMA group at University of North Carolina, Chapel Hill and IVPLab at Chinese University of Hong Kong, supervised by Prof. Dinesh Manocha and Prof. Xiaogang Wang, respectively.
Research Interests
vision-based crowd understanding, image segmentation, and image processing, etc.
News
- One paper From Contexts to Locality: Ultra-high Resolution Image Segmentation via Locality-aware Contextual Correlation accepted in ICCV 2021! The code will be released.
- The code of HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions has been released.
- The code of Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation has been released.
- Three papers accepted in CVPR 2021!
- One paper accepted in ECCV 2020!
- One paper accepted in IEEE VR 2020!
Publications
Segmentation
- From Contexts to Locality: Ultra-high Resolution Image Segmentation via Locality-aware Contextual Correlation
Qi Li, Weixiang Yang, Wenxi Liu*, Yuanlong Yu, Shengfeng He
ICCV 2021 [pdf][arxiv][code] - Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation,
Weixiang Yang, Qi Li, Wenxi Liu*, Yuanlong Yu, Yuexin Ma, Shengfeng He, Jia Pan
CVPR 2021 [pdf][code] - Reciprocal Transformations for Unsupervised Video Object Segmentation
Sucheng Ren, Wenxi Liu, Yongtuo Liu, Haoxin Chen, Guoqiang Han, Shengfeng He
CVPR 2021 - Real-Time Hierarchical Supervoxel Segmentation via a Minimum Spanning Tree
Bo Wang, Yiliang Chen, Wenxi Liu, Jing Qin, Yong Du, Guoqiang Han, Shengfeng He
IEEE Trans. Image Processing (TIP), 2020 - Learning Long-term Structural Dependencies for Video Salient Object Detection
Bo Wang, Wenxi Liu, Guoqiang Han, Shengfeng He
IEEE Trans. Image Processing (TIP), 2020 - Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery
Xiaosheng Yan, Feigege Wang, Wenxi Liu*, Yuanlong Yu, Shengfeng He, Jia Pan
ICCV 2019 [arxiv] - Context-aware Spatio-recurrent Curvilinear Structure Segmentation
Feigege Wang, Yue Gu, Wenxi Liu*, Yuanlong Yu, Shengfeng He, Jia Pan
CVPR 2019 [pdf] - Enhancement Mask for Hippocampus Detection and Segmentation
Dengsheng Chen, Wenxi Liu*, You Huang, Tong Tong, Yuanlong Yu
IEEE International Conference on Information and Automation (ICIA), 2018 [arxiv] - SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection
Shengfeng He, Rynson W. H. Lau, Wenxi Liu, Zhe Huang, Qingxiong Yang
International Journal of Computer Vision (IJCV), 2015
Crowd and Multi-robots
- End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps
Ke Guo, Wenxi Liu, Jia Pan
CVPR 2022 - Monocular Camera-based Complex Obstacle Avoidance via Efficient Deep Reinforcement Learning
Jianchuan Ding, Lingping Gao, Wenxi Liu, Haiyin Piao, Jia Pan, Zhenjun Du, Xin Yang, Baocai Yin
IEEE Trans. Circuits Syst. Video Techn. (TCSVT), 2022 - Coarse-to-Fine Person Re-Identification with Auxiliary-Domain Classification and Second-Order Information Bottleneck
Anguo Zhang, Yueming Gao, Yuzhen Niu, Wenxi Liu, Yongcheng Zhou
CVPR 2021 - A Vision-based Irregular Obstacle Avoidance Framework via Deep Reinforcement Learning
Lingping Gao, Jianchuan Ding, Wenxi Liu, Haiyin Piao, Yuxin Wang, Xin Yang, Baocai Yin
IROS 2021 - CrowdGAN: Identity-free Interactive Crowd Video Generation and Beyond
Liangyu Chai, Yongtuo Liu, Wenxi Liu, Guoqiang Han, Shengfeng He
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 - Crowd Counting via Cross-stage Refinement Networks
Yongtuo Liu, Qiang Wen, Haoxin Chen, Wenxi Liu, Jing Qin, Guoqiang Han, Shengfeng He
IEEE Transactions on Image Processing (TIP), 2020 - Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Navigation in Complex Scenarios
Tingxiang Fan, Pinxin Long, Wenxi Liu, Jia Pan
International Journal on Robotics Research (IJRR), 2020 - Learning Resilient Behaviors for Navigation Under Uncertainty
Tingxiang Fan, Pinxin Long, Wenxi Liu, Jia Pan, Ruigang Yang, Dinesh Manocha
ICRA 2020 - Over-crowdedness Alert! Forecasting the Future Crowd Distribution
Yuzhen Niu, Weifeng Shi, Wenxi Liu*, Shengfeng He, Jia Pan, Antoni B. Chan
Arxiv 2020 [arxiv] - Recurrent Distillation based Crowd Counting
Yue Gu, Wenxi Liu*
Arxiv 2020 [arxiv] - Deformable Object Tracking with Gated Fusion
Wenxi Liu, Yibing Song, Dengsheng Chen, Shengfeng He, Yuanlong Yu, Tao Yan, Rynson W. H. Lau
IEEE Trans. Image Processing (TIP), 2019 [arxiv][code] - Extraversion Measure for Crowd Trajectories
Wenxi Liu, Chun-Yang Zhang, Genggeng Liu, Yaru Su, Naixue Xiong
IEEE Trans. on Industrial Informatics (TII), Special Section on Emerging Trends Issues and Challenges in Edge Artificial Intelligence, 2019 - Getting Robots Unfrozen and Unlost in Dense Pedestrian Crowds
Tingxiang Fan, Xinjing Cheng, Jia Pan, Pinxin Long, Wenxi Liu, Ruigang Yang, Dinesh Manocha
IEEE Robotics and Automation Letters (RAL), 2019 - Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning
Pinxin Long, Tingxiang Fan, Xinyi Liao, Wenxi Liu, Hao Zhang, Jia Pan
ICRA 2018 - Deep-Learned Collision Avoidance Policy for Distributed Multiagent Navigation
Pinxin Long, Wenxi Liu, Jia Pan
IEEE Robotics and Automation Letters (RAL), 2017 - Exemplar-AMMs: Recognizing Crowd Movements From Pedestrian Trajectories
Wenxi Liu, Rynson W. H. Lau, Xiaogang Wang, Dinesh Manocha
IEEE Trans. Multimedia (TMM), 2016 [preprint] - Robust individual and holistic features for crowd scene classification
Wenxi Liu, Rynson W. H. Lau, Dinesh Manocha
Pattern Recognition (PR), 2016 - BRVO: Predicting pedestrian trajectories using velocity-space reasoning
Sujeong Kim, Stephen J. Guy, Wenxi Liu, David Wilkie, Rynson W. H. Lau, Ming C. Lin, Dinesh Manocha
International Journal on Robotics Research (IJRR), 2015 - Leveraging Long-Term Predictions and Online Learning in Agent-Based Multiple Person Tracking
Wenxi Liu, Antoni B. Chan, Rynson W. H. Lau, Dinesh Manocha
IEEE Trans. Circuits Syst. Video Techn. (TCSVT), 2015 [preprint] - Data-driven sequential goal selection model for multi-agent simulation
Wenxi Liu, Zhe Huang, Rynson W. H. Lau, Dinesh Manocha
ACM Symposium on Virtual Reality Software and Technology (VRST) 2014 - A statistical similarity measure for aggregate crowd dynamics
Stephen J. Guy, Jur van den Berg, Wenxi Liu, Rynson W. H. Lau, Ming C. Lin, Dinesh Manocha
ACM Trans. Graph. (TOG), 2012 - Crowd simulation using Discrete Choice Model
Wenxi Liu, Rynson W. H. Lau, Dinesh Manocha
IEEE Virtual Reality (VR) 2012
Miscellaneous
- Comment-Guided Semantics-Aware Image Aesthetics Assessment
Yuzhen Niu, Shanshan Chen, Bingrui Song, Zhixian Chen, Wenxi Liu
IEEE Trans. Circuits Syst. Video Techn. (TCSVT), 2022 - Perceptual-aware and Restorable Real-time Image Downscaling
Yuzhen Niu, Luwei Zheng, Jiaqi Lin, Jianbin Wu, Wenxi Liu*
ICME 2022 - HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions
Yuzhen Niu, Jianbin Wu, Wenxi Liu*, Wenzhong Guo, Rynson W.H. Lau
IEEE Transactions on Image Processing (TIP), 2021 [code] - EBRB cascade classifier for imbalanced data via rule weight updating
Yang-Geng Fu, Hong-Yun Huang, Yu Guan, Ying-Ming Wang, WenxiLiu*, Wei-Jie Fang
Knowledge-Based Systems (KBS), 2021 - Boundary-aware RGBD Salient Object Detection with Cross-modal Feature Sampling
Yuzhen Niu, Guanchao Long, Wenxi Liu*, Wenzhong Guo, Shengfeng He
IEEE Trans. Image Processing (TIP), 2020 - Mapping in a Cycle: Sinkhorn Regularized Unsupervised Learning for Point Cloud Shapes
Lei Yang, Wenxi Liu, Zhiming Cui, Nenglun Chen, Wenping Wang
ECCV 2020 [code] - Recurrent Enhancement of Visual Comfort for Casual Stereoscopic Photography
Yuzhen Niu, Qingyang Zheng, Wenxi Liu*, Wenzhong Guo
IEEE Virtual Reality (VR) 2020 (Oral) - 3D Deconvolutional Networks for the Unsupervised Representation Learning of Human Motions
Chun-Yang Zhang, Yongyi Xiao, Jin-Cheng Lin, C. L. Philip Chen, Wenxi Liu, Yuhong Tong
IEEE Transactions on Cybernetics 2020 - Stereoscopic Image Generation from Light Field with Disparity Scaling and Super-Resolution
Tao Yan, Jianbo Jiao, Wenxi Liu, Rynson WH Lau
IEEE Trans. Image Processing (TIP), 2020 - Generating Stereoscopic Images with Convergence Control Ability from a Light Field Image Pair
Tao Yan, Yiming Mao, Jianming Wang, Wenxi Liu, Xiaohua Qian, and Rynson Lau
IEEE Trans. Circuits Syst. Video Techn. (TCSVT), 2020 - Single Image Reflection Removal Beyond Linearity
Qiang Wen, Yinjie Tan, Jing Qin, Wenxi Liu, Guoqiang Han, Shengfeng He
CVPR 2019 - Deep compression of probabilistic graphical networks
Chun-Yang, Zhang, Qi Zhao, C.L. Philip Chen, Wenxi Liu
Pattern Recognition (PR), 2019 - Combined X-ray and facial videos for phoneme-level articulator dynamics
Hui Chen, Lan Wang, Wenxi Liu, Pheng-Ann Heng
The Visual Computer, 2010
