BIO

I am a second-year Ph.D. student in the Computer Science Department at the University of Rochester (UofR). My advisor is Prof. Chenliang Xu. Before that, I received my master and bachelor degree in University of Science and Technology of China (USTC) under the supervision of Prof. Nenghai Yu and Prof. Bin Liu.

I am focusing on human related topic (e.g. face animation and stylization, 3D face reconstruction, deepfake detection e.t.c.). And I also working on general object detection/segmentation and optical character recognition (OCR). Outside of research, I love mountaineering and have summitted the Muztagh Ata and Chola mountains.

E-Mail: slc0826@mail.ustc.edu.cn; slc1253858918@gmail.com

Education

• 2022.09-now Department of Computer Science, UofR. (Ph.D. Student)
  • Supervisor: Prof. Chenliang Xu
• 2018.09-2021.06 Department of Electronic Engineering and Information Science, USTC. (Master Degree)
  • Supervisor: Prof. Nenghai Yu and Prof. Bin Liu
• 2014.09-2018.06 Department of Electronic Engineering and Information Science, USTC. (Bachelor Degree)
  • I received bachelor degree in USTC in 2018. Befor that, the 30th China Physics Olympiad (CPhO) gave me the qualification to recommend to the USTC, and I still have a strong interest in physics.

PUBLICATION

• [ 1] Luchuan Song, Bin Liu, Guojun Yin, et al. TACR-Net: Editing on Deep Video and Voice Portraits. ACM'MM2021.
• [ 2] Luchuan Song, Zheng Fang, et al. Adaptive Face Forgery Detection in Cross Domain. ECCV2022.
• [ 3] Luchuan Song, Xiaodan Li, et al. Face Forgery Detection via Symmetric Transformer. ACM'MM2022.
• [ 4] Luchuan Song, Guojun Yin, Bin Liu, et al. FSFT-NET: FACE TRANSFER VIDEO GENERATION WITH FEW-SHOT VIEWS. IEEE ICIP2021.
• [ 5] Luchuan Song, Bin Liu, Nenghai Yu. Talking Face Video Generation With Expression. ICIG2021.
• [ 6] Jingqun Tang, Wenming Qian, Luchuan Song, et al. Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning. ECCV 2022.
• [ 7] Zhenchao Jin, Dongdong Yu, Luchuan Song, et al. You Should Look at All Objects. ECCV 2022.
• [ 8] Jiaxuan Bai, Bin Liu, Luchuan Song. I Know Your Keyboard Input: A Robust Keystroke Eavesdropper Based-on Acoustic Signals. ACM'MM2021.
• [ 9] Kun Zhao, Bin Liu, Luchuan Song., et al. CASCADED RESIDUAL DENSITY NETWORK FOR CROWD COUNTING. IEEE ICIP2019.
• [10] Yinan He, Bei Gan, Siyu Chen, Yichun Zhou, Guojun Yin, Luchuan Song, Lu Sheng, Jing Shao, Ziwei Liu. ForgeryNet: A Versatile Benchmark For Comprehensive Forgery Analysis. CVPR2021

TEACHING

• Information Theory, 2018 Fall, USTC

PROFESSIONAL ACTIVITIES

• I am reviewer of CVPR (2021, 2022, 2023) / ICCV 2023 / AAAI 2021 / TMM / TCSVT