Congcong Li's Homepage

Stay Hungry. Stay Foolish.

I received the B.Eng. degree from University of Electronic Science and Technology of China in 2018, and then became a Master student at University of Chinese Academy of Sciences. My research interests include computer vision and deep learning, particularly focusing on Object Detection, Domain Adaptation and Visual Question Answering(VQA).

GitHub · Google Scholar · Blog

Educations

• 2014 - 2018
  B.Eng. in University of Electronic Science and Technology of China

• 2018 - Present
  M. student in University of Chinese Academy of Sciences

Experience

• 2017 - 2018
  Intern at SAP Chengdu, China

Publications

• End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection
  Congcong Li, Xinyao Wang, Longyin Wen, Dexiang Hong, Tiejian Luo, Libo Zhang
  Conference on Computer Vision and Pattern Recognition (CVPR), 2022
• Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)
  Dexiang Hong, Congcong Li, Longyin Wen, Xinyao Wang, Libo Zhang
• Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
  Congcong Li, Dawei Du, Libo Zhang, Longyin Wen, Tiejian Luo, Yanjun Wu, Pengfei Zhu
  European Conference on Computer Vision (ECCV), 2020
• Iterative Knowledge Distillation for Automatic Check-Out
  Libo Zhang, Dawei Du, Congcong Li, Yanjun Wu, Tiejian Luo
  IEEE Transactions on Multimedia (TMM), 2020
• Data Priming Network for Automatic Check-Out
  Congcong Li, Dawei Du, Libo Zhang, Tiejian Luo, Yanjun Wu, Qi Tian, Longyin Wen, Siwei Lyu
  ACM International Conference on Multimedia (ACM), 2019

Projects

• SSD: High quality implementation of SSD in PyTorch.
• Xblog: A powerful and responsive blog system powered by laravel 5.5.
• Vizer: Boxes and masks visualization tools.
• flask_ishuhui: Comic reading website built by flask. Clear project structure.
• DPNet: This repository implements DPNet with PyTorch 1.0.1.
• StateLayout: A custom layout that can easily switch different states.
• Deep Q Network: Toy implementation of Deep Q Network.