I’m currently a tenure-track assistant professor at John Hopcroft Center (JHC) for Computer Science of Shanghai Jiao Tong University (SJTU). My research interest mainly lies on Computer Vision and Multimedia. I received my Ph.D. degree in Department of Electrical & Computer Engineering at McMaster University, supervised by Prof. Jun Chen. During the Ph.D., I visited Computer Vision Lab at Michigan State University, where I’m adviced by Prof. Xiaoming Liu.

I received the Shanghai Pujiang Talent Program in 2022, the Chinese Government Award for Outstanding Self-financed Students Abroad in 2021, a Canada Graduate Scholarship from Natural Sciences and Engineering Research Council of Canada (NSERC) in 2021, and a Borealis AI Fellowship in 2020. My research has been supported by the Young Scientists Fund of the National Natural Science Foundation of China, and many big tech companies.

Lab Website: SJTU Multimedia Lab

Prospective Students

I am always looking for enthusiastic and self-motivated students to work together on computer vision and mutimedia related topics. Please email me with your CV and transcripts if you are interested.

There are one master’s position and one postdoc position available in Fall 2024. Please contact me ASAP if interested.

News

  • [2024/2]   Two papers are accepted by CVPR 2024
  • [2023/7]   Three papers are accepted by ACM MM 2023 (Two orals!)
  • [2023/7]   One paper is accepted by ICCV 2023
  • [2023/3]   One paper is accepted by CVPR 2023
  • [2022/9]   One paper is accepted by NeurIPS 2022
  • [2022/3]   One paper is accepted by CVPR 2022

Selected Publications

* Equal contribution, Corresponding author

 

[ICCV] AccFlow: Backward Accumulation for Long-Range Optical Flow [Paper]
Guangyang Wu, Xiaohong Liu, Kunming Luo*, Xi Liu*, Qingqing Zheng, Shuaicheng Liu, Xinyang Jiang, Guangtao Zhai, Wenyi Wang
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.


 

[ACMMM] FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table [Paper]
Wenhao Li*, Guangyang Wu*, Wenyi Wang, Peiran Ren, Xiaohong Liu
The 31st ACM International Conference on Multimedia, 2023.


 

[ACMMM] Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancement [Oral] [Paper]
Yunlong Dong, Xiaohong Liu, Yixuan Gao, Xunchu Zhou, Tao Tan, Guangtao Zhai
The 31st ACM International Conference on Multimedia, 2023.


 

[ACMMM] StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability [Oral] [Paper]
Tengchuan Kou, Xiaohong Liu, Wei Sun, Jun Jia, Xiongkuo Min, Guangtao Zhai, Ning Liu
The 31st ACM International Conference on Multimedia, 2023.


 

[CVPR] Hierarchical Fine-Grained Image Forgery Detection and Localization [Paper]
Xiao Guo, Xiaohong Liu, Zhiyuan Ren, Steven Grosz, Iacopo Masi, Xiaoming Liu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.


 

[TCSVT] PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization [Paper]
Xiaohong Liu, Yaojie Liu, Jun Chen, Xiaoming Liu
IEEE Transactions on Circuits and Systems for Video Technology, 2022.


 

[CVPR] Video Frame Interpolation Transformer [Paper]
Zhihao Shi*, Xiangyu Xu*, Xiaohong Liu, Jun Chen, and Ming-Hsuan Yang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.


 

[IEEE ITS] GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing [Paper]
Xiaohong Liu, Zhihao Shi, Zijun Wu, Jun Chen, and Guangtao Zhai
IEEE Transactions on Intelligent Transportation Systems, 2022.


 

[IEEE TIP] Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference [Paper]
Xiaohong Liu, Kangdi Shi, Zhe Wang, and Jun Chen
IEEE Transactions on Image Processing, 2021.


 

[WACV] End-to-End Trainable Video Super-Resolution Based on A New Mechanism for Implicit Motion Estimation and Compensation [Paper]
Xiaohong Liu, Lingshi Kong, Yang Zhou, Jiying Zhao, and Jun Chen
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020.


 

[ICCV] GridDehazeNet: Attention based Multi-Scale Network for Image Dehazing [Paper]
Xiaohong Liu*, Yongrui Ma*, Zhihao Shi, and Jun Chen
IEEE/CVF International Conference on Computer Vision (ICCV), 2019.


 

[IEEE TIP] Robust Multi-Frame Super-Resolution Based on Spatially Weighted Half-Quadratic Estimation and Adaptive BTV Regularization [Paper]
Xiaohong Liu, Lei Chen, Wenyi Wang, and Jiying Zhao
IEEE Transactions on Image Processing, 2018.

Services

Professional Service:

  • NTIRE 2023 Quality Assessment of Video Enhancement Challenge Organizer
  • IC 2023 AI for Medicine Area Organization Committee
  • CGI 2023 Workshops/Special Session Chair
  • VRIH Special issue: 3D Medical Image Processing and Analysis Organizer
  • Serve as an Associate Editor of the ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) from Jan. 2024

Reviewer:

  • Journal: IEEE TPAMI, IEEE TIP, IEEE TIFS, IEEE TMM, IEEE TCSVT, IEEE TITS, IEEE TBC, Pattern Recognition
  • Conference: ICCV 2021, CVPR 2022, ECCV 2022, CVPR 2023, ICCV 2023, AAAI 2024, CVPR 2024, ECCV 2024