Dr. Shuo Chen (陈硕)

(Pronouns: he/him/his)

Research Scientist
TikTok, Singapore

Email: shanshuo1992 at gmail dot com
[Github] [Google Scholar] [LinkedIn] [Twitter]

About Me (CV)

I am a Research Scientist at TikTok Singapore, working on Text-to-Video generation.

Previously, I was a PhD candidate at University of Amsterdam under the supervision of Prof. Cees Snoek and Dr. Pascal Mettes.

I received my master's degree in Department of Electronic Engineering, Tsinghua University under the supervision of Prof. Qingmin Liao and Dr. Fei Zhou. I did undergrad in School of Internet of Things at Nanjing University of Posts and Telecommunications.

I was a visiting student of Multimedia Research Center at Shenzhen Institute of Advanced Technology under the supervision of Prof. Yu Qiao.


We are looking for research interns to work on Text-to-Video. Feel free to email me if you are interested!

News

▸ 2024.01: We released MagicVideo-V2.
▸ 2023.07: I successfully defended my doctoral degree. View my thesis here.
▸ 2023.05: I start my full-time job at TikTok, Singapore.
▸ 2023.04: One paper is accepted by ICMR 2023.
▸ 2022.12: I start my intern at Snap, New York.
▸ 2022.08: I had a fantastic internship experience advised by Dr. Erhan Gundogdu and Dr. Loris Bazzani at Amazon Berlin.
▸ 2022.05: I start my intern at Amazon, Berlin.
▸ 2021.10: Two papers are accepted by BMVC 2021.
▸ 2021.09: I had a fantastic internship experience advised by Dr. Tan Yu at Baidu Research.
▸ 2021.07: One paper is accepted by ICCV 2021. This paper is also accepted by ICCV'21 workshop on Structured Rpresentations for Video Understanding.
▸ 2021.06: I start my intern at Baidu Research, Beijing.
▸ 2020.03: One paper is accepted by ICMR 2020.
▸ 2019.10: One paper is accepted by ACMMM 2019.
▸ 2018.1.15: I join the VIS Lab group.

Publications

MagicVideo-V2:Multi-Stage High-Aesthetic Video Generation
Weimin Wang*, Jiawei Liu*, Zhijie Lin, Jiangqiao Yan, Shuo Chen, Chetwin Low, Tuyen Hoang, Jie Wu, Jun Hao Liew, Hanshu Yan, Daquan Zhou, Jiashi Feng
arXiv, 2024.
[arXiv] [project]

Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation
Shuo Chen, Yingjun Du, Pascal Mettes, Tao Hu and Cees G.M. Snoek
ACM International Conference on Multimedia Retrieval (ICMR), 2023. (Oral)
[arXiv] [code]

R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition
Shuo Chen, Tan Yu, and Ping Li
arXiv, 2022.
[arXiv] [code]

MVT: Multi-view Vision Transformer for 3D Object Recognition
Shuo Chen, Tan Yu, and Ping Li
British Machine Vision Conference (BMVC), 2021.
[arXiv] [code]

Diagnosing Errors in Video Relation Detectors
Shuo Chen, Pascal Mettes, and Cees G.M. Snoek
British Machine Vision Conference (BMVC), 2021.
[arXiv] [supplemental material] [code]

Social Fabric: Tubelet Compositions for Video Relation Detection
Shuo Chen, Zenglin Shi, Pascal Mettes, and Cees G.M. Snoek
IEEE International Conference on Computer Vision (ICCV), 2021.
[arXiv] [code]

Interactivity Proposals for Surveillance Videos
Shuo Chen, Pascal Mettes, Tao Hu and Cees G.M. Snoek
ACM International Conference on Multimedia Retrieval (ICMR), 2020. (Oral)
[pdf] [ACM] [code]

Interactive Exploration of Journalistic Video Footage through Multimodal Semantic Matching
Sarah Ibrahimi, Shuo Chen, Devanshu Arya, Arthur Camara, Yunlu Chen, Tanja Crijns, Maurits van der Goes, Thomas Mensink, Emiel van Miltenburg, Daan Odijk, William Thong, Jiaojiao Zhao,and Pascal Mettes
ACM International Conference on Multimedia (ACMMM), 2019.
[ACM]

Research on Transfer Learning Algorithm based on Generating Weighted Subspaces
Shuo Chen
Master Thesis (in Chinese), 2017.
[pdf]

Visual Domain Adaptation using Weighted Subspace Alignment
Shuo Chen, Fei Zhou, Qingmin Liao
IEEE International Conference on Visual Communications and Image Processing (VCIP), 2016. (Oral)
[pdf] [IEEE] [slides] [code]

Education Background

Research Experience

Teaching

University of Amsterdam

Internships

Professional Activities