Chuming Lin (林楚铭)

Chuming is a Senior Researcher at Tencent Youtu Lab, Shanghai.

He got his Master degree from School of Computer Science, Fudan University in 2020, supervised by Prof. Bo Yan. Previously, he received the Bachelor degree from Fudan University in 2017.

His research interests include computer vision and deep learning, particularly focusing on AIGC, temporal action localization and image/video enhancement tasks.

Email  /  Google Scholar  /  Github

Recent news

  • 08/2024 – Tencent 2024H1 Outstanding Contributor

  • 05/2024 – 腾讯云智能视频转译(视频翻译)功能上线: 视频转译体验入口

  • 10/2023 – 腾讯云智能小样本数智人通用版本上线: 数智人产品入口

  • 08/2023 – Tencent 2023H1 Outstanding Contributor

  • 04/2023 – 正式对外推出腾讯云智能小样本数智人定制版: 公众号介绍

  • 11/2022 – Our CRI on GAN inversion is accepted by AAAI'23, with the acceptance rate to be 19.6%.

  • 08/2022 – Tencent 2022H1 Outstanding Contributor

  • 06/2022 – Our CDSR on blind image super-resolution is accepted by ACMMM'22, with the acceptance rate to be 27.9%.

  • 09/2021 – Our S2K on blind image super-resolution is accepted by NeurIPS'21, with the acceptance rate to be 26%.

  • 04/2021 – Our Team Imagination is the winner of CVPR NTIRE 2021 Challenge on Video Spatial-Temporal Super-Resolution.

  • 04/2021 – Our Team Imagination is the runner-up of CVPR NTIRE 2021 Challenge on Video Spatial Super-Resolution.

  • 03/2021 – Our AFSD on temporal action localization is accepted by CVPR'21, with the acceptance rate to be 23.7%.

  • 11/2019 – Our DBG on temporal action proposal is accepted by AAAI'20, with the acceptance rate to be 20.6%. The code of our DBG is released at [ActionDetection-DBG], which achieves Top 1 performance on ActivityNet Challenge on Temporal Action Proposals.

  • 11/2018 – Our FFCVSR on video super-resolution is accepted by AAAI'19, with the acceptance rate to be ONLY 16.2%.


Publications (* equal contribution, # first student author)

SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion Model
W. Tan*, C. Lin*, C. Xu, X. Ji, J. Zhu, C. Wang, Y. Fu.
2024
arXiv
RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network
X. Ji, C. Lin, Z. Ding, Y. Tai, J. Yang, J. Zhu, X. Hu, J. Zhang, D. Luo, C. Wang.
2024
arXiv
High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets
Y. Wang, C. Lin, D. Luo, Y. Tai, Z. Zhang, Y. Xie.
AAAI Conference on Artificial Intelligence (AAAI), 2023
arXiv / Code (Official)

Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution
Y. Zhou*, C. Lin*, D. Luo, Y. Liu, Y. Tai, C. Wang, M. Chen.
ACM International Conference on Multimedia (ACM MM), 2022
arXiv / Paper / Code (Official)

Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
C. Lin*, C. Xu*, D. Luo, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang and Y. Fu.
Computer Vision and Pattern Recognition (CVPR), 2021
arXiv / Paper / Code (Official)

Fine-Grained Motion Estimation for Video Frame Interpolation
B. Yan, W. Tan, C. Lin#, L. Shen.
IEEE Transactions on Broadcasting (IEEE Trans. Broadcast.), 2020
Paper

Fast Learning of Temporal Action Proposal via Dense Boundary Generator
C. Lin*, J. Li*, Y. Wang, Y. Tai, D. Luo, Z. Cui, C. Wang, J. Li, F. Huang and R. Ji.
AAAI Conference on Artificial Intelligence (AAAI), 2020
arXiv / Code (Official)

No. 1 performace on ActivityNet Challenge on Temporal Action Proposals

Frame and Feature-Context Video Super-Resolution
B. Yan, C. Lin#, W. Tan.
AAAI Conference on Artificial Intelligence (AAAI), 2019
arXiv / Code (Official)

Cycle-IR: Deep Cyclic Image Retargeting
W. Tan, B. Yan, C. Lin, X. Niu.
IEEE Transactions on Multimedia (TMM), 2019
arXiv / Code (Official)

Foreground Detection in Surveillance Video with Fully Convolutional Semantic Network
C. Lin, B. Yan, W. Tan.
IEEE International Conference on Image Processing (ICIP), 2018
Paper

Awards

  • 2024H1 Tencent Outstanding Contributor

  • 2023H1 Tencent Outstanding Contributor

  • 2022H1 Tencent Outstanding Contributor

  • 2021 Winner Award of CVPR NTIRE 2021 Challenge on Video Super-Resolution: Spatial-Temporal (Team name: Imagination)

  • 2021 Runner-Up Award of CVPR NTIRE 2021 Challenge on Video Super-Resolution: Spatial (Team name: Imagination)

  • 2020 Shanghai outstanding graduates

  • 2018 and 2019 Huawei Graduate Scholarship of Fudan University

  • 2017 2nd Prize of Graduate Mathematical Contest in Modeling, China

  • 2013 1st Prize of National Olympiad in Informatics in Province (NOIP)



For the style of my personal website, please refer to the wonderful page from Jon Barron.