Tsu-Jui (Ray) Fu

I am currently a 2nd-year Ph.D. student at UCSB, advised by William Wang. My research interest lies in natural language processing (NLP) and computer vision (CV). Primarily, I work on language grounding and interacting with environments using language. Besides, I am also interested in information extraction and video analysis. My goal is to bridge the gap between vision and language via the AI system.

I finish my B.S. in National Tsing-Hua University (NTHU) and work with Shan-Hung Wu, Wei-Yun Ma, Chun-Yi Lee, and Hwann-Tzong Chen.


Research Assistant
2019 - Now

Microsoft Azure AI
Research Intern
Summer 2021

Microsoft Research
Research Intern
Summer 2020

Preferred Networks
Research Intern
Summer 2019

Academia Sinica
Research Assistant
2018 - 2019

H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction
Tsu-Jui Fu*, Jhih-Wei Chen*, Chen-Kang Lee, and Wei-Yun Ma
Findings of ACL'21 (Long)
Paper / Slide / Video / Code

Semi-Supervised Policy Initialization for Playing Games with Language Hints
Tsu-Jui Fu and William Yang Wang
NAACL'21 (Short)
Paper / Slide / Video / Code

L2C: Describing Visual Differences Needs Semantic Understanding of Individuals
An Yan, Xin Eric Wang, Tsu-Jui Fu, and William Yang Wang
EACL'21 (Short)

Multimodal Style Transfer Learning for Outdoor Vision-and-Language Navigation
Wanrong Zhu, Xin Eric Wang, Tsu-Jui Fu, An Yan, Pradyumna Narayana, Kazoo Sone, Sugato Basu, and William Yang Wang
EACL'21 (Long)
Paper / Code

SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning
Tsu-Jui Fu, Xin Eric Wang, Scott Grafton, Miguel Eckstein, and William Yang Wang
EMNLP'20 (Long)
Paper / Slide / Code

Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler
Tsu-Jui Fu, Xin Eric Wang, Matthew Peterson, Scott Grafton, Miguel Eckstein, and William Yang Wang
ECCV'20 (Spotlight)
Paper / Slide / Video / Model

Why Attention? Analyzing and Remedying BiLSTM Deficiency in Modeling Cross-Context for NER
Peng-Hsuan Li, Tsu-Jui Fu, and Wei-Yun Ma
AAAI'20 (Oral)
Paper / Code

A Distributed Scheme for Accelerating Semantic Video Segmentation on An Embedded Cluster
Tsu-Jui Fu*, Hsuan-Kung Yang*, Kuan-Wei Ho, Po-Han Chiang and Chun-Yi Lee
ICCD'19 (Oral)
Paper / Video

Adversarial Active Exploration for Inverse Dynamics Model Learning
Zhang-Wei Hong, Tsu-Jui Fu, Tzu-Yun Shann, Yi-Hsiang Chang, and Chun-Yi Lee
CoRL'19 (Oral)

GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction
Tsu-Jui Fu, Peng-Hsuan Li, and Wei-Yun Ma
ACL'19 (Long)
Paper / Slide / Code

Attentive and Adversarial Learning for Video Summarization
Tsu-Jui Fu, Shao-Heng Tai, and Hwann-Tzong Chen
WACV'19 (Oral)
Paper / Video / Code

Region-Semantics Preserving Image Synthesis
Kang-Jun Liu, Tsu-Jui Fu, and Shan-Hung Wu
Paper / Video / Code

Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Tsu-Jui Fu, and Chun-Yi Lee
Paper / Video

Speed Reading: Learning to Read ForBackward via Shuttle
Tsu-Jui Fu and Wei-Yun Ma
EMNLP'18 (Long)
Paper / Code

Dynamic Video Segmentation Network
Yu-Syuan Xu, Tsu-Jui Fu*, Hsuan-Kung Yang*, and Chun-Yi Lee
Paper / Video / Code

Template from Jon Barron and Shao-Hua Sun