Dr. Zheng (Thomas) Tang

Dr. Zheng (Thomas) Tang

Senior Deep Learning Engineer at NVIDIA, expert in computer vision and machine learning

Bio

Dr. Zheng (Thomas) Tang is currently a Senior Deep Learning Engineer of Metropolis at NVIDIA (2021~). Dr. Tang was previously an Applied Scientist of Amazon One at Amazon (2019~2021). He received his Ph.D. degree in Electrical & Computer Engineering (ECE) from the University of Washington (UW) in 2019.

His research interests include intelligent transportation systems, multi-/single-camera object tracking, re-identification, pose estimation, action recognition, camera calibration, synthetic data generation, biometric identification, and other topics in computer vision and machine learning. He has 6 filed U.S. patents and 20+ publications in peer-reviewed journals and conference proceedings in these areas. He has been an Associate Editor (AE) (2021~) for IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT) and an Organizing Committee Member (2020~) for the AI City Challenge Workshops in conjunction with CVPR. He is also an Area Chair of ACM MM 2024 and MLSP 2021. As a reviewer, he frequently serves for academic journals and international conferences, such as IJCV, T-PAMI, T-IP, T-MM, T-CSVT, T-ITS, NeurIPS, CVPR, ICCV, ICASSP, ICME, etc. Dr. Tang received the Best AE Award of T-CSVT in 2021.

The team he led achieved rank #1 in Track 1 (Traffic Flow Analysis) and Track 3 (Multi-camera Vehicle Detection and Reidentification) at the 2nd AI City Challenge Workshop in CVPR 2018. His paper was a finalist of 2 Best Student Paper Awards at ICPR 2016.

News

  • [Mar. 2024] Fusing Real-Time AI With Digital Twins highlighted at the keynote of NVIDIA GTC 2024
  • [Mar. 2023] NVIDIA Metropolis Microservices 1.0 released, where I developed the Multi-Camera Tracking app and trained with synthetic data from Omniverse
  • [Jan. 2023] Released the 7th AI City Challenge Worshop in conjunction with CVPR 2023
  • [Dec. 2022] NVIDIA TAO Toolkit 4.0 released, where I developed people re-identification and pose-based action recognition networks as well as end-to-end video analytics pipelines
  • [Oct. 2022] "Label-Efficient Learning on Video Data" accepted as a special issue to T-CSVT
  • [Feb. 2022] Received the Best AE Award of T-CSVT for 2021
  • [Jan. 2022] Released the 6th AI City Challenge Worshop in conjunction with CVPR 2022
  • [Oct. 2021] Served as an Area Chair of MLSP 2021
  • [May 2021] Started a new job at NVIDIA joining the Metropolis team
  • [Jan. 2021] Released the 5th AI City Challenge Workshop in conjunction with CVPR 2021
  • [Dec. 2020] Joined the Editorial Board of T-CSVT (Impact Factor: 5.859) as an Associate Editor (AE)
  • [Sep. 2020] Amazon One launched, where I worked at the research team and filed two U.S. patents
  • [May 2020] Source code of "PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data" (ICCV 2019) released on GitHub
  • [Jan. 2020] Released the 4th AI City Challenge Worshop in conjunction with CVPR 2020
  • [Jul. 2019] "PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data" accepted to ICCV 2019
  • [Jun. 2019] Graduated with a Ph.D. degree in ECE from UW
  • [Feb. 2019] "CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification" accepted to CVPR 2019 (Oral)
  • [Jun. 2018] Achieved rank #1 in Track 1: Traffic Flow Analysis (Demo) and Track 3: Multi-camera Vehicle Detection and Reidentification (Demo) of the 2nd AI City Challenge Workshop in CVPR 2018
  • [Jun. 2018] "Joint Multi-View People Tracking and Pose Estimation for 3D Scene Reconstruction" accepted to ICME 2018 (Oral)
  • [Aug. 2017] Selected as the winner of Track 2: AI City Applications (Demo) at the 1st AI City Challenge Workshop in SmartWorld 2017
  • [May 2017] "Online-Learning-Based Human Tracking Across Non-Overlapping Cameras" accepted to T-CSVT
  • [Dec. 2016] "Camera Self-Calibration from Tracking of Moving Persons" selected as a finalist of 2 Best Student Paper Awards at ICPR 2016
  • [Dec. 2015] "Multiple-Kernel Adaptive Segmentation and Tracking (MAST) for Robust Object Tracking" accepted to ICASSP 2016 (Oral)
  • [Jun. 2014] Graduated with a B.Sc. (Eng.) degree from the Joint Programme between BUPT and QMUL with First Class Honours