Jiyang Gao
Hi, welcome to my webpage! Email: jiyanggao1203 at gmail dot com
About Me
I’m Jiyang Gao (高继扬), currently an Executive Director at Momenta. I am leading several teams, including highway autonomous driving system, planning, localization & odometry, sensor calibration, and AI Infra. I was in charge of camera perception, during that period we reframed the engineering framework in perception team, and delivered the Perception OneModel (all features, all cameras, all platforms, one model), which is now served in multiple OEM SOP projects.
Before Momenta, I worked for Waymo as a tech lead & senior software engineer. The projects I delivered include ML-based prediction (VectorNet is one of the published results in this project), online lane estimation, offline auto-labeling and LiDAR perception.
I got my PhD degree from USC in 2018 Nov, advised by Prof. Ram Nevatia, with a focus on CV&DL. I obtained my B.S. degree from Tsinghua University in 2015. I did internship at Sensetime in 2015, at Google Research during 2017 summer, at Google Cloud AI in 2018.
Education
- Doctor of Philosophy (Ph.D), Electrical Engineering
- Advisor: Prof. Ram Nevatia
- Bachelor of Engineering (B.E), Microelectronics
- Graduated with Excellent Thesis Award
Selected Publications
TNT: Target-driveN Trajectory Prediction
Hang Zhao*, Jiyang Gao*, Tian Lan, Chen Sun, Benjamin Sapp, Balakrishnan Varadarajan, Yue Shen, Yi Shen, Yuning Chai, Cordelia Schmid, Congcong Li, Dragomir Anguelov
CoRL 2020
[Paper]
VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation
Jiyang Gao*, Chen Sun*, Hang Zhao, Yi Shen, Dragomir Angulov, Congcong Li, Cordelia Schmid
CVPR 2020
[Paper] [Waymo Blog] [VentureBeat]
STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
Zhishuai Zhang, Jiyang Gao, Junhua Mao, Yukai Liu, Dragomir Angulov, Congcong Li
CVPR 2020
[Paper]
End-to-End Multi-View Fusion for 3D Object Detection in Lidar Point Clouds
Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Tom Ouyang, James Guo, Jiquan Ngiam, Vijay Vasudevan
CoRL 2019
[Paper]
Mac: Mining Activity Concepts for Language-based Temporal Localization
Runzhou Ge, Jiyang Gao, Kan Chen, Ram Nevatia
WACV 2019
[Paper] [Code]
NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
Jiyang Gao, Jiang Wang, Shengyang Dai, Li-Jia Li, Ram Nevatia
ICCV 2019
[Paper]
CTAP: Complementary Temporal Action Proposal Generation
Jiyang Gao*, Kan Chen*, Ram Nevatia
ECCV 2018
[Paper] [Code]
Revisiting Temporal Modeling for Video-based Person ReID
Jiyang Gao, Ram Nevatia
Tech Report 2018
[Paper] [Code]
Motion-Appearance Co-Memory Networks for Video Question Answering
Jiyang Gao*, Runzhou Ge*, Kan Chen, Ram Nevatia
CVPR 2018
[Paper]
Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
Kan Chen, Jiyang Gao, Ram Nevatia
CVPR 2018
[Paper] [Code]
Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
Jiyang Gao, James Guo, Zhen Li, Ram Nevatia
Tech Report 2017
[Paper]
TALL: Temporal Activity Localization via Language Query
Jiyang Gao, Chen Sun, Zhenheng Yang and Ram Nevatia
ICCV 2017
[Paper] [Code] [Video]
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Jiyang Gao*, Zhenheng Yang*, Kan Chen, Chen Sun and Ram Nevatia
ICCV 2017
[Paper] [Code]
Cascaded Boundary Regression for Temporal Action Detection
Jiyang Gao, Zhenheng Yang, Ram Nevatia
BMVC 2017
[Paper] [Code] [THUMOS-14 Results]
RED: Reinforced Encoder-Decoder Network for Action Anticipation
Jiyang Gao, Zhenheng Yang, Ram Nevatia
BMVC 2017
[Paper] [Video]
Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation
Zhenheng Yang, Jiyang Gao, Ram Nevatia
BMVC 2017
[Paper] [Video]
Professional Services
Conference Reviewer for CVPR, ICCV, ECCV, ICLR, AAAI, ACM MM, ACCV, WACV,
Journal Reviewer for IEEE PAMI, International Journal of Computer Vision (IJCV), Computer Vision and Image Understanding (CVIU), IEEE Transactions on Multimedia, Pattern Recognition, IEEE Transactions on Cybernetics.