About Me

I’m Ruoteng LI, currently a Research Scientist at ByteDance AI-Lab, working intenstively on video understanding & recommendation, multi-modality learning. I am also a joint Lecturer in Electrical Engineering Faculty in National University of Singapore (NUS) in 2022 - 2023. I obtained my Ph.D degree from Electrical & Computer Engineering department, NUS in 2020 (from 2016-2020). My supervisor was Prof. Cheong Loong Fah and Prof. Robby T. Tan, who gave me untold valuable guidance and indispensable encouragements. Before that, I completed my bachelor degree from NUS and my high school education at Yao Hua High School in China. [Full CV]

I was a visiting student in Cambridge Image Analysis (CIA) group led by Dr. Carola-Bibiane Schönlieb at the Department Applied Mathematics and Theoretical Physics (DAMTP), Cambridge University. I was collaborating with Dr. Angelica I. Aviles-Rivero and Dr. Qingnan Fan on Image Processing problems.

I had my internship in Google, with DayDream, AR Core team in 2020 Summer. My supervisor Josh Hernandez helped me tremendously on solving AR tracking problem using intrinsic image decomposition. (slides)

Full CV / Resume / Google Scholar

Research

Conference & Journal

Estimating reflectance layer from a single image: Integrating reflectance guidance and shadow/specular aware learning
Yeying Jin, Ruoteng Li*, Wenhan Yang, Robby T. Tan
In Proceedings of the AAAI Conference on Artificial Intelligence 2023

AdAM: Few-Shot Generation via Adaption-Aware Kernel Modulation
In Submission to TPAMI
TPAMI

Hybrid Warping Fusion for Video Frame Interpolation
Yu Li, Ye Zhu, Ruoteng Li*, Xintao Wang, Yue Luo, Ying Shan
International Journal of Computer Vision (IJCV)

Realistic Large-Scale Fine-Depth Dehazing Dataset from 3D Videos
In Submission to NeurIPS Dataset Track
NeurIPS

Single Image Reflection removal via learning with multi-image constraints
Yingda Yin, Qingnan Fan, Dongdong Chen, Yujie Wang, Angelica Aviles-Rivero, Ruoteng Li*, Carola-Bibiane Schnlieb, Baoquan Chen
Arxiv

Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
In Submission to TPAMI
TPAMI
arXiv / codes / supplementary / BibTex

Object Tracking using Spatio-Temporal Networks for Future Prediction Location
Ruoteng Li*, Yuan Liu*, Yu Cheng, Robby T. Tan, Xiubao Sui
ECCV 2020
paper / code / supplementary

All-in-One Bad Weather Removal using Fusion Search
Ruoteng Li, Robby T. Tan, Loong-Fah Cheong
CVPR 2020
paper / supplementary

RainFlow: Optical Flow under Rain Streaks and Rain Veiling Effect
Ruoteng Li, Robby T. Tan, Loong-Fah Cheong, Angelica I. Aviles-Rivero, Qingnan Fan, Carola-bibiane Schönlieb
ICCV 2019
paper / code / supplementary

GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision
Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Qingnan Fan, Robby T. Tan, Carola-bibiane Schönlieb.
MICCAI 2019
paper

Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
Ruoteng Li, Loong-Fah Cheong, Robby T. Tan
CVPR, 2019
paper / code / supplementary / arXiv

Robust Optical Flow in Rainy Scenes
Ruoteng Li, Robby T. Tan, Loong-Fah Cheong,
ECCV, 2018
paper / code / supplementary / arXiv

Preprints

Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network
Ruoteng Li, Loong-Fah Cheong, Robby T. Tan,
arXiv preprints, 2017
arXiv