Scholar
Xin Tao
Google Scholar ID: sQ30WyUAAAAJ
Kuaishou
Citations & Impact
Citations
4,966
H-index
27
i10-index
39
Publications
20
Co-authors
50
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- * Perception-Oriented Video Frame Interpolation via Asymmetric Blending, CVPR 2024
- * Feature Decoupling-Recycling Network for Fast Interactive Segmentation, ACM MM 2023
- * Scene-Generalizable Interactive Segmentation of Radiance Fields, ACM MM 2023
- * Compression-Aware Video Super-Resolution, CVPR 2023
- * DeViT: Deformed Vision Transformers in Video Inpainting, ACM MM 2022
- * Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling, CVPR 2022
- - Tech Transfers:
- * Kling text-to-video tool, June 2024
- * 2D digital human live streaming platform VirtualLive, August 2023
- * Deployed dozens of cutting-edge video editing algorithms in Kuaiying App
Research Experience
- - Tech Lead, Visual Generation Group, Kuaishou, November 2024 - present
- - Mixed Reality Group, Y-tech, Kuaishou, November 2023 - 2024
- - Video Processing and Analysis Group, Video Technology, Kuaishou, November 2020 - 2023
- - Senior Researcher, Youtu Lab, Tencent, November 2018 - 2020
- - Research Intern, Creative Technologies Lab, Adobe Research, June 2016 - August 2016, Advisor: Jue Wang
- - Research Assistant, Laboratory of Quantum Nonlinear Photonics (QNP), Shanghai Jiao Tong University, January 2011 - January 2013, Advisor: Guangqiang He
Education
- - Ph.D. in Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), August 2013 - September 2018, Advisor: Prof. Jiaya Jia
- - B. Eng. in Information Engineering, Shanghai Jiao Tong University (SJTU), 2013, Advisor: Prof. Guangqiang He
Background
- - Research Interest: Visual restoration and generation
- - Professional Field: Video generation and editing
- - Biography: Currently a Senior Researcher and Tech Lead in the Visual Generation Group at Kuaishou Technology, responsible for research and tech transfer of video editing algorithms, as well as a comprehensive system of 2D digital human for live streaming.
Miscellany
- Actively seeking talented and self-motivated research interns or full-time researchers to join the team.
