Dr. Zheng (Thomas) Tang

Dr. Zheng (Thomas) Tang

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

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

About me

Posts

Announcing the Official Release of the Metropolis Multi-Camera Tracking AI Workflow

2 minute read

Published:

Announcing the official release of the Metropolis Multi-Camera Tracking AI Workflow, featured in NVIDIA GTC’24 Keynote by Jensen Huang. This innovative solution accelerates the development of vision AI applications for large spaces, enhancing safety, efficiency, and management across various industries. Leveraging NVIDIA’s cutting-edge tools, this workflow offers a validated path to production, customizable AI models, and comprehensive support, enabling seamless development from simulation to deployment. Join us in transforming infrastructure and operations with advanced AI technology.

Advancing AI with NVIDIA Omniverse at CVPR 2024: AI City Challenge Highlights

2 minute read

Published:

As the lead organizer of the AI City Challenge at CVPR, I’m excited to highlight our progress with NVIDIA Omniverse, which provided the largest indoor synthetic dataset for over 700 teams from nearly 50 countries. This dataset, essential for developing AI models to improve efficiency in retail, warehouse management, and traffic systems, included 212 hours of video across 90 virtual environments. Our global collaboration with ten prestigious institutions underscores the effort to advance AI for smart cities and automation. NVIDIA’s innovations, like Omniverse Cloud Sensor RTX, will further accelerate autonomous system development. Join the Omniverse community to stay updated and connected.

Simplifying Industrial Automation with Real-Time Multi-Camera AI

2 minute read

Published:

In the heart of the industrial automation revolution, the Metropolis multi-camera tracking system emerges as a beacon of innovation, seamlessly integrating with NVIDIA’s AI suite to redefine efficiency and safety in complex industrial settings. Developed by a pioneering software engineer, Metropolis creates a real-time, comprehensive map from hundreds of camera feeds, guiding autonomous mobile robots through intricate environments with unparalleled precision. This fusion of real-time AI and digital twin technology not only showcases the potential to drastically reduce operational downtime but also marks a significant leap forward in the quest for smarter, more responsive industrial ecosystems. Through this lens, we glimpse the future of automation, where digital precision and human ingenuity converge to create harmonious, highly optimized workplaces.

Introducing Metropolis AI Workflows & Microservices 1.0: Revolutionizing Multi-Camera Tracking

3 minute read

Published:

The Metropolis AI Workflows & Microservices 1.0 is officially live and is set to revolutionize the way enterprises and our ecosystem approach centralized perception across an array of matrixed sensors. One of the most exciting features of this release is the Multi-Camera Tracking app, which I had the pleasure of developing. The app is a reference architecture for video analytics applications that tracks people across multiple cameras and provides the counts of unique people seen over time. This is also known as Multi-Target Multi-Camera (MTMC) tracking.

My Work on the NVIDIA TAO Toolkit 4.0: People Re-Identification and Pose-Based Action Recognition Networks

2 minute read

Published:

NVIDIA has recently announced the release of the TAO Toolkit 4.0, which includes several exciting new features and enhancements. As a developer who has contributed to the toolkit, I’m thrilled to share my experience working on the people re-identification and pose-based action recognition networks, as well as the end-to-end video analytics pipelines on the Triton Inference Server.

Waymaker Church: Making a Way in the Wilderness

3 minute read

Published:

Starting a new church can be a daunting task. However, when a group of Christ followers feel called by God to spread the Gospel, they know they must answer. That’s exactly what happened with the team at Waymaker Church.

Macy Lee and I Tie the Knot: Our Intimate Vow Ceremony

1 minute read

Published:

Love is a beautiful thing, and nothing symbolizes that more than a wedding ceremony. Macy Lee and I, two lovebirds who have been together for a while, decided to take our relationship to the next level by tying the knot in an intimate vow ceremony. We chose the beautiful rooftop lounge of Augusta Apartments in Seattle, WA, to exchange our vows in front of our church and lab friends.

A Thanksgiving Proposal: How I Popped the Question to Macy Lee

3 minute read

Published:

Love is in the air, and when it’s time to take that big step, nothing is more exciting than the perfect proposal. For me, that moment came on Thanksgiving Day in 2021, at my friend’s house in Bothell, WA. I proposed to my girlfriend, Macy Lee, and I’m thrilled to say that she said yes!

Behind the Innovation: My Work on Amazon One

1 minute read

Published:

I am excited to share my experience working on the Amazon One project, an innovative identity service that uses people’s palm for payment, entry, and more. As a member of the research team that developed and launched Amazon One, I had the opportunity to contribute to this groundbreaking technology in significant ways.

Robust Video Object Tracking via Camera Self-Calibration - My Ph.D. Defense Experience

1 minute read

Published:

I am pleased to announce that I have successfully passed my Ph.D. Dissertation Defense in the Department of Electrical and Computer Engineering (ECE) at the University of Washington (UW). This has been a long and challenging journey, and I am grateful for the support of my supervisory committee, colleagues, sponsors, family, friends, and my faith.

Winning the People’s Choice Award at Code for the Kingdom Hackathon - Seattle 2019

1 minute read

Published:

As a software developer, I love to participate in hackathons to test my skills and knowledge, as well as to collaborate with fellow tech enthusiasts. One of the most exciting hackathons I have participated in is Code for the Kingdom (C4TK) - Seattle 2019, where my team won the People’s Choice Award.

Becoming an Elder: A Calling to Serve the Church

2 minute read

Published:

I still remember the feeling of excitement and awe when I received the news that I had been elected to be a Session Elder of the University Presbyterian Church (UPC). It was an honor that came with great responsibility and a strong sense of duty to serve my fellow members and the church community as a whole.

portfolio

publications

Melody Extraction from Polyphonic Audio of Western Opera: A Method Based on Detection of the Singer’s Formant

Published in 2014 International Society for Music Information Retrieval Conference, 2014

[Paper] [Craze] [Poster]

Recommended citation: Zheng Tang and Dawn AA Black. "Melody Extraction from Polyphonic Audio of Western Opera: A Method Based on Detection of the Singer’s Formant". 2014 International Society for Music Information Retrieval Conference (ISMIR 2014). pp. 161-166. 2014. http://www.terasoft.com.tw/conf/ismir2014/proceedings/T029_329_Paper.pdf

Multiple-Kernel Adaptive Segmentation and Tracking (MAST) for Robust Object Tracking

Published in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, 2016

[Paper] [Slides]

Recommended citation: Zheng Tang, Jenq-Neng Hwang, Yen-Shuo Lin and Jen-Hui Chuang. "Multiple-Kernel Adaptive Segmentation and Tracking (MAST) for Robust Object Tracking". Proceedings of 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016). pp. 3064-3068. 2016. http://ieeexplore.ieee.org/document/7471849

Single-Camera and Inter-Camera Vehicle Tracking and 3D Speed Estimation Based on Fusion of Visual and Semantic Features

Published in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition - 2nd AI City Challenge Workshop, 2018

[Paper] [Code] [Slides] [Poster] [Demo1] [Demo2]

Recommended citation: Zheng Tang, Gaoang Wang, Hao Xiao, Aotian Zheng and Jenq-Neng Hwang. "Single-Camera and Inter-Camera Vehicle Tracking and 3D Speed Estimation Based on Fusion of Visual and Semantic Features". Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2018). pp. 108-115. 2018. http://openaccess.thecvf.com/content_cvpr_2018_workshops/w3/html/Tang_Single-Camera_and_Inter-Camera_CVPR_2018_paper.html

Self-Calibration of Traffic Surveillance Cameras Based on Moving Vehicle Appearance and 3-D Vehicle Modeling

Published in 2018 IEEE International Conference on Image Processing, 2018

[Paper]

Recommended citation: Na Wang, Haiqing Du, Yong Liu, Zheng Tang and Jenq-Neng Hwang. "Self-Calibration of Traffic Surveillance Cameras Based on Moving Vehicle Appearance and 3-D Vehicle Modeling". Proceedings of 2018 IEEE International Conference on Image Processing (ICIP 2018). pp. 3064-3068. 2018. https://ieeexplore.ieee.org/document/8451478

The 2019 AI City Challenge

Published in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition - 3rd AI City Challenge Workshop, 2019

[Paper] [Website]

Recommended citation: Milind Naphade, Zheng Tang, Ming-Ching Chang, David C Anastasiu, Anuj Sharma, Rama Chellappa, Shuo Wang, Pranamesh Chakraborty, Tingting Huang, Jenq-Neng Hwang and Siwei Lyu. "The 2019 AI City Challenge". Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2019). pp. 452-460. 2019. http://openaccess.thecvf.com/content_CVPRW_2019/html/AI_City/Naphade_The_2019_AI_City_Challenge_CVPRW_2019_paper.html

CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

Published in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019

[Paper] [Presentation] [Slides] [Poster] [Website]

Recommended citation: Zheng Tang, Milind Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, David Anastasiu and Jenq-Neng Hwang. "CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification". Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019). pp. 8797-8806. 2019. https://arxiv.org/abs/1903.09254

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

Published in 2019 IEEE/CVF International Conference on Computer Vision, 2019

[Paper] [Code] [Poster]

Recommended citation: Zheng Tang, Milind Naphade, Stan Birchfield, Jonathan Tremblay, William Hodge, Ratnesh Kumar, Shuo Wang and Xiaodong Yang. "PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data". Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV 2019). pp. 211-220. 2019. http://arxiv.org/abs/2005.00673

The 4th AI City Challenge

Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition - 4th AI City Challenge Workshop, 2020

[Paper] [Website]

Recommended citation: Milind Naphade, Shuo Wang, David Anastasiu, Zheng Tang, Ming-Ching Chang, Xiaodong Yang, Liang Zheng, Anuj Sharma, Rama Chellappa and Pranamesh Chakraborty. "The 4th AI City Challenge". Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2020). 2020. https://arxiv.org/abs/2004.14619

The 5th AI City Challenge

Published in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition - 5th AI City Challenge Workshop, 2021

[Paper] [Website]

Recommended citation: Milind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Xiaodong Yang, Yue Yao, Liang Zheng, Pranamesh Chakraborty, Christian E. Lopez, Anuj Sharma, Qi Feng, Vitaly Ablavsky and Stan Sclaroff. "The 5th AI City Challenge". Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2021). 2021. https://arxiv.org/abs/2104.12233

The 6th AI City Challenge

Published in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition - 6th AI City Challenge Workshop, 2022

[Paper] [Website]

Recommended citation: Milind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Archana Venkatachalapathy, Anuj Sharma, Qi Feng, Vitaly Ablavsky, Stan Sclaroff, Pranamesh Chakraborty, Alice Li, Shangru Li and Rama Chellappa. "The 6th AI City Challenge". Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2022). 2022. https://arxiv.org/abs/2204.10380

The 7th AI City Challenge

Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition - 7th AI City Challenge Workshop, 2023

[Paper] [Website]

Recommended citation: Milind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Qi Feng, Vitaly Ablavsky, Stan Sclaroff, Pranamesh Chakraborty, Sanjita Prajapati, Alice Li, Shangru Li, Krishna Kunadharaju, Shenxin Jiang and Rama Chellappa. "The 7th AI City Challenge". Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023). 2023. https://arxiv.org/abs/2304.07500

The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework

Published in IEEE Transactions on Circuits and Systems for Video Technology, 2023

[Paper]

Recommended citation: Chao Wang and Zheng Tang. "The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework". IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT). 2024. http://ieeexplore.ieee.org/document/10182291

The 8th AI City Challenge

Published in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition - 8th AI City Challenge Workshop, 2024

[Paper] [Website]

Recommended citation: Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Pranamesh Chakraborty, Sanjita Prajapati, Quan Kong, Norimasa Kobori, Munkhjargal Gochoo, Munkh-Erdene Otgonbold, Ganzorig Batnasan, Fady Alnajjar, Ping-Yang Chen, Jun-Wei Hsieh, Xunlei Wu, Sameer Satish Pusegaonkar, Yizhou Wang, Sujit Biswas and Rama Chellappa. "The 8th AI City Challenge". Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2024). 2024. https://arxiv.org/abs/2404.09432

WSSGCN: Wide Sub-stage Graph Convolutional Networks

Published in Neurocomputing, 2024

Abstract

Graph Convolutional Networks (GCNs) have emerged as a potent tool for learning graph representations, finding applications in a plethora of real-world scenarios. Nevertheless, a significant portion of deep learning research has predominantly concentrated on enhancing model performance via the construction of deeper GCNs. Regrettably, the efficacy of training deep GCNs is marred by two fundamental weaknesses: the inadequacy of conventional methodologies in handling heterogeneous networks, and the exponential surge in model complexity as network depth increases. This, in turn, imposes constraints on their practical utility. To surmount these inherent limitations, we propose an innovative approach named the Wide Sub-stage Graph Convolutional Network (WSSGCN). Our method is an outcome of meticulous observations drawn from classical and graph convolutional networks, aimed at rectifying the constraints associated with traditional GCNs. Our strategy involves the conception of a staged convolutional network framework that mirrors the fundamental tenets of the step-by-step learning process akin to human cognition. This framework prioritizes three distinct forms of consistency: response-based, feature-based, and relationship-based. Our approach involves three tailored convolutional networks capturing node/edge, subgraph, and global features. Additionally, we introduce a novel method to expand graph width for efficient GCN training. Empirical validation on benchmarks highlights WSSGCN’s superior accuracy and faster training versus conventional GCNs. WSSGCN triumphs over traditional GCN constraints, significantly enhancing graph representation learning.

Recommended citation: Chao Wang, Zheng Tang and Hailu Xu. "WSSGCN: Wide Sub-stage Graph Convolutional Networks". Neurocomputing. vol. 602, p. 128273. 2024. https://www.sciencedirect.com/science/article/pii/S0925231224010440

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.