Changan Chen 陈昌安

I am a Ph.D. student in Computer Science at UT Austin advised by Prof. Kristen Grauman. I am also a visiting researcher at Facebook AI Research. My broad interests are computer vision, machine learning and robotics. Currently, I'm working on embodied learning and audio-visual learning.

Previously, I spent a wonderful year working with Prof. Greg Mori on sports video analysis and efficient deep learning, eight months working with Prof. Alexandre Alahi on social navigation in crowds, and eight months working with Prof. Manolis Savva on relational graph reasoning for navigation.

My first name is pronounced as /tʃæn'æn/ with the g being silent.

CV | E-Mail | Google Scholar | Github | Twitter

News
Feb 2021 Organizing the first SoundSpaces Challenge at the Embodied AI Workshop, CVPR 2021!
Jan 2021 One paper accepted to ICLR 2021
July 2020 Released a curated reading list for embodied vision: awesome-embodied-vision
July 2020 One paper accepted to IROS 2020 and two papers accepted to ECCV 2020
May 2020 Joining Facebook AI Research as a visiting researcher
Publications
sym

[NEW] Learning Audio-Visual Dereverberation
Changan Chen, Wei Sun, David Harwath, Kristen Grauman
arXiv 2021
paper | project

sym

[NEW] Semantic Audio-Visual Navigation Star
Changan Chen, Ziad Al-Halah, Kristen Grauman
CVPR 2021
paper | project | code

sym

[NEW] Learning to Set Waypoints for Audio-Visual Navigation Star
Changan Chen, Sagnik Majumder, Ziad Al-Halah, Ruohan Gao, Santhosh K. Ramakrishnan, Kristen Grauman
ICLR 2021
paper | project | code

sym

VisualEchoes: Spatial Image Representation Learning through Echolocation Star
Ruohan Gao, Changan Chen, Carl Schissler, Ziad Al-Halah, Kristen Grauman
ECCV 2020
paper | project | code

sym

SoundSpaces: Audio-Visual Navigation in 3D Environments Star
Changan Chen*, Unnat Jain*, Carl Schissler, Sebastia Vicenc Amengual Gari, Ziad Al-Halah, Vamsi Krishna Ithapu, Philip Robinson, Kristen Grauman
ECCV 2020 (spotlight)
paper | project | code | website

sym

Relational Graph Learning for Crowd Navigation Star
Changan Chen*, Sha Hu*, Payam Nikdel, Greg Mori, Manolis Savva
IROS 2020
paper | code

sym

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning Star
Changan Chen, Yuejinag Liu, Sven Kreiss, Alexandre Alahi
ICRA 2019
paper | code

sym

Constraint-Aware Deep Neural Network Compression Star
Changan Chen, Frederick Tung, Naveen Vedula, and Greg Mori
ECCV 2018
paper | code

Presentations & Talks
June 2021 Invited talk at Facebook Reality Labs, "Learning Audio-Visual Dereverberation" (PPT)
June 2021 Invited talk at EPIC Workshop, CVPR 2021, "Semantic Audio-Visual Navigation" (PPT)
Sept. 2020 Invited talk at CS391R: Robot Learning at UT Austin, ""Audio-Visual Navigation" (PPT)
Dec. 2018 Invited talk at SwissAI Meetup, "Navigation in Crowds: From 2D Navigation to Visual Navigation"
Nov. 2018 Invited talk at Swiss Machine Learning Day, "Crowd-aware Robot Navigation with Attention-based DRL"
May 2018 Poster presentation at SFU-ZJU Joint Symposium, "Constraint-aware Deep Neural Network Compression"
Media Coverage
Facebook AI Blog 2021 Habitat Challenge launches to advance embodied AI research
Facebook AI Blog New milestones in embodied AI
VentureBeat Facebook releases tools to help AI navigate complex environments
ZDNet Facebook is building home robots to help you find your ringing phone
MIT Technology Review Facebook is training robot assistants to hear as well as see
Affiliations
                   
ZJU
2014-2016
SFU
2016-2019
EPFL
2018
UT AUSTIN
2019 - present
FAIR
2020 - present

Template credits: Unnat