I am a PhD student in the College of Engineering and Computer Science (CECS) at the Australian National University (ANU). I am also a research student at the Australian Centre for Robotic Vision (ACRV) and the Vision-Ask-Answer-Act Lab (V3A).

I am under the supervision of Prof. Stephen Gould (ANU), Dr. Qi Wu (UoA) and Prof. Lexing Xie (ANU).

Prior to that, in Nov’2018, I received my bachelor degree of engineering in mechatronic systems with a first-class honours in the College of Engineering and Computer Science at ANU. In 2018, I was also a part-time research student at the Data61, CSIRO, working on human pose and shape visualization.

I have a broad research interests in computer vision, natural language processing and robotics. Currently, my main research focus is on the problem of Embodied Vision-and-Language (E-V&L), and inparticular Vision-and-Language Navigation . I believe, E-V&L has the great potential to merge a wide range of visiolinguistic research to create an embodied interative system which is practical to assist human in real-world.

News

2022.05.10

• Invited talk by the NLP Lab at the Fudan University, really enjoyed chatting with everyone!

2022.03.14

• I have started a research internship at the Creative Intelligence Lab in Adobe Research in San Jose, California, US!!! 😆😆😆

2022.03.02

• Our paper Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation has been accepted to CVPR 2022! 😊 I am so happy to share lots of thoughts about VLN in this paper! See you guys in New Orleans! ❤️ PDF Code
• Paper HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation by Yanyuan Qiao, Yuankai Qi, Peng Wang, Qi Wu and myself has been accepted to CVPR 2022! Congrats Yanyuan on the first paper in her PhD! 😀 PDF Code

2021.08.17

• Paper The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation by Yuankai Qi, Zizheng Pan, Ming-Hsuan Yang, Anton van den Hengel, Qi Wu and myself has been accepted to ICCV 2021! 😀 PDF Code

2021.04.10

• Paper Learning Structure-Aware Semantic Segmentation with Image-Level Supervision by Jiawei Liu, Dr. Jing Zhang, Prof. Nick Barnes and myself, has been accepted to IJCNN 2021! Congrats Jiawei on his first paper in computer vision! 😀 PDF

2021.03.16

• Our Thinking-VLN repo is online! Come to enjoy our immature ideas and share your thoughts! Just for FUN thinking!

2021.03.06

• Our paper A Recurrent Vision-and-Language BERT for Navigation has been accepted to CVPR 2021 as an Oral paper with 3 strong accepts! 😆😆😆 PDF Code

2020.10.05

• I gave a guest lecture in the Deep Learning Course at ANU (ENGN8536) about Vision and Language Research! My first lecture at Uni! Nervous and Fun! 😀 PDF

2020.09.26

• Our paper Language and Visual Entity Relationship Graph for Agent Navigation has been accepted to NeurIPS 2020! 😀 PDF Code

2020.09.15

• Our paper Sub-Instruction Aware Vision-and-Language Navigation has been accepted to EMNLP 2020! My first paper! 😊 PDF FGR2R Data

Research

A Recurrent Vision-and-Language BERT for Navigation
Yicong Hong, Qi Wu, Yuankai Qi, Cristian Rodriguez-Opazo, Stephen Gould
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
PDF Code

Language and Visual Entity Relationship Graph for Agent Navigation
Yicong Hong, Cristian Rodriguez-Opazo, Yuankai Qi, Qi Wu, Stephen Gould
Conference on Neural Information Processing Systems (NeurIPS), 2020
PDF Code

Sub-Instruction Aware Vision-and-Language Navigation
Yicong Hong, Cristian Rodriguez-Opazo, Qi Wu, Stephen Gould
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
PDF FGR2R Data

The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Yuankai Qi, Zizheng Pan, Yicong Hong, Ming-Hsuan Yang, Anton van den Hengel, Qi Wu
International Conference on Computer Vision Systems (ICCV), 2021
PDF Code