Guanzhi Wang

I am a Master's student at the Stanford Vision and Learning Lab, where I have been fortunate working with Prof. Fei-Fei Li, Prof. Yuke Zhu and Dr. Jim Fan.

I obtained my B.S. degree from the Hong Kong University of Science and Technology, where I have been lucky to work with Prof. Chi-Keung Tang and Prof. Yu-Wing Tai. Previously, I was a research intern at Tencent YouTu.

My research interests lie in the area of computer vision and robotics. I am passionate about building intelligent agents to acquire rich and robust visual representations proactively and solve real-world robotic tasks efficiently.

Email / Google Scholar / GitHub / LinkedIn

News

[2021.03] I will be joining as a PhD student at Caltech in Fall 2021.
[2021.03] I will be TAing CS231n in Spring 2021.
[2021.03] Deep Video Matting accepted to CVPR 2021.
[2020.12] iGibson v1 released.
[2020.07] RubiksNet accepted to ECCV 2020.
[2019.07] LADN accepted to ICCV 2019.

Publications (* indicates equal contribution)
	iGibson, a Simulation Environment for Interactive Tasks in Large Realistic Scenes Bokui Shen, Fei Xia, Chengshu Li, Roberto Martín-Martín, Linxi Fan, Guanzhi Wang, Claudia D’Arpino, Shyamal Buch, Sanjana Srivastava, Lyne P. Tchapmi, Micael E. Tchapmi, Kent Vainio, Josiah Wong, Li Fei-Fei, Silvio Savarese International Conference on Intelligent Robots and Systems (IROS), 2021 (under review) [paper] [project page] [code] We presented iGibson, a novel simulation environment for developing interactive robotic agents in large-scale realistic scenes.
	RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition Linxi Fan, Shyamal Buch, Guanzhi Wang, Ryan Cao, Yuke Zhu, Juan Carlos Niebles, Li Fei-Fei European Conference on Computer Vision (ECCV), 2020 [paper] [project page] [video] [supplementary] [code] We proposed RubiksNet, a new efficient architecture for video action recognition based on a proposed learnable 3D spatiotemporal shift operation (RubiksShift).
	LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup Qiao Gu, Guanzhi Wang, Mang Tik Chiu, Yu-Wing Tai, Chi-Keung Tang International Conference on Computer Vision (ICCV), 2019 [paper] [project page] [code] [dataset] We proposed a local adversarial disentangling network for facial makeup and de-makeup, using multiple and overlapping local discriminators in a content-style disentangling network.

Technical Reports
	Drowsiness Tracking from Video Recordings Obtained from Consumer-grade Electronic Devices Guanzhi Wang, Thomas Heldt Technical Report, 2018 [paper] We proposed a facial landmark based method to extract blink duration and to quantify drowsiness scale from video recordings obtained from consumer-grade electronic devices.
	Velocity Vector Preserving Trajectory Simplification Guanzhi Wang, Zhenmei Shi, Cheng Long, Ya Gao, Raymond Chi-Wing Wong Technical Report, 2018 [paper] [code] We designed a novel algorithm to simplify a trajectory such that the number of points after simplification is minimized under the constraint that the velocity-based error does not exceed a given tolerance.