Xihui Liu

Postdoc Scholar, Darrell Group / BAIR / EECS Department UC Berkeley xihui.liu.me@gmail.com xihui.liu@berkeley.edu Google Scholar   CV

About me

I am a Postdoc Scholar at EECS Department and BAIR at UC Berkeley, advised by Prof. Trevor Darrell. I obtained my Ph.D. degree from Multimedia Lab (MMLab), the Chinese University of Hong Kong, supervised by Prof. Xiaogang Wang and Prof. Hongsheng Li. I received bachelor's degree in Electronic Engineering in Tsinghua University (THU) in 2017. My research interests cover the broad area of computer vision and deep learning, with special emphasis on multimodal language and vision. and image synthesis and editing. I was awarded Adobe Research Fellowship 2020, and selected as one of the EECS Rising Stars 2021.

Education

• Ph.D, Department of Electronic Engineering / Multimedia Lab (MMLab), The Chinese University of Hong Kong. (2017 to 2021)
  Advised by Prof. Xiaogang Wang and Prof. Hongsheng Li.

• Bachelor, Department of Electronic Engineering, Tsinghua University. (2013 to 2017)
  

Working Experience

• Postdoc Scholar at UC Berkeley. (August 2021 to now)
  Advised by Prof Trevor Darrell.

• Research intern at NVIDIA Research. (2020)
  Worked on video synthesis with Ming-Yu Liu and Ting-Chun Wang.

• Research intern at Adobe Research. (2019)
  Worked on open-vocabulary open-domain image editing with Zhe Lin, Jianming Zhang, Handong Zhao, and Quan Tran.

• Research assistant at Multimedia Lab (MMLab), CUHK. (2016)
  Worked on object detection in videos with Kai Kang, supervised by Prof. Xiaogang Wang.

Publications

• More Control for Free! Image Synthesis with Semantic Diffusion Guidance [Project Page] [Slides]
  Xihui Liu, Dong Huk Park, Samaneh Azadi, Gong Zhang, Arman Chopikyan, Yuxiao Hu, Humphrey Shi, Anna Rohrbach, Trevor Darrell
  2021.

• BridgeFormer: Bridging Video-text Retrieval with Multiple Choice Questions [Project Page]
  Yuying Ge, Yixiao Ge, Xihui Liu, Dian Li, Ying Shan, Xiaohu Qie, Ping Luo
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

• Benchmark for Compositional Text-to-Image Synthesis
  Dong Huk Park, Samaneh Azadi, Xihui Liu, Trevor Darrell, Anna Rohrbach
  Thirty-third Conference on Neural Information Processing Systems (NeurIPS) Dataset and Benchmark Track, 2021.

• Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions [Video] [Slides] [Code]
  Xihui Liu, Zhe Lin, Jianming Zhang, Handong Zhao, Quan Tran, Xiaogang Wang, Hongsheng Li
  European Conference on Computer Vision (ECCV), 2020.

• Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis [Code] [Slides]
  Xihui Liu, Guojun Yin, Jing Shao, Xiaogang Wang, Hongsheng Li
  Thirty-third Conference on Neural Information Processing Systems (NeurIPS), 2019.

• Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing [Code]
  Xihui Liu, Zihao Wang, Jing Shao, Xiaogang Wang, Hongsheng Li
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

• Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data
  Xihui Liu, Hongsheng Li, Jing Shao, Dapeng Chen, Xiaogang Wang
  European Conference on Computer Vision (ECCV), 2018.

• CAMP: Cross-modal Adaptive Message Passing for Text-Image Retrieval [Code]
  Zihao Wang*, Xihui Liu*, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, Jing Shao
  International Conference on Computer Vision (ICCV), 2019.

• Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
  Dapeng Chen, Hongsheng Li, Xihui Liu, Yantao Shen, Jing Shao, Zejian Yuan, Xiaogang Wang
  European Conference on Computer Vision (ECCV), 2018.

• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
  Xihui Liu*, Haiyu Zhao*, Maoqing Tian, Lu Sheng, Jing Shao, Shuai Yi, Junjie Yan, Xiaogang Wang
  International Conference on Computer Vision (ICCV), 2017.

• Localization Guided Learning for Pedestrian Attribute Recognition
  Pengze Liu, Xihui Liu, Junjie Yan, Jing Shao,
  British Machine Vision Conference (BMVC), 2018.

• Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification
  Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan, Shengjin Wang, Hongsheng Li, Xiaogang Wang
  International Conference on Computer Vision (ICCV), 2017.

• Object Detection in Videos With Tubelet Proposal Networks
  Kai Kang, Hongsheng Li, Tong Xiao, Wanli Ouyang, Junjie Yan, Xihui Liu, Xiaogang Wang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

Academic Services

Reviewer of the following conferences and journals:

• Outstanding Reviewer for CVPR 2019 and ICLR 2021.

• CVPR, ICCV, ECCV, NeruIPS, ICML, ICLR, AAAI.

• IJCV, TCSVT, NeuroComputing, TMM.

Teaching Experience

Teaching Assistant of the following courses in The Chinese University of Hong Kong:

• ELEG 5491, Introduction to Deep Learning [Course website], Spring 2019.

• ENGG 5202, Pattern Recognition, Fall 2017, Spring 2020.

• ELEG 5760, Machine Learning for Signal Processing Applications, Fall 2018.

• ENGG 2450A, Probability and Statistics for Engineers, Spring 2018, Fall 2020.

• Summer Tutorial, Potential Inspiration in Electronic Engineering, Summer 2018.

• ENGG 2420B, Complex Analyis and Differential Equations for Engineers, Fall 2019.

• ENGG 2740A, Differential Equations for Engineers, Spring 2021.