Yizhou Wang
Senior Deep Learning Engineer at NVIDIA · Ph.D., University of Washington
I am a Senior Deep Learning Engineer at NVIDIA, working on computer vision and deep learning for smart cities and smart spaces (such as warehouses and factories). My research centers on computer vision, autonomous driving, 3D perception, multi-object tracking, and camera–radar sensor fusion. Before NVIDIA, I was a Senior Machine Learning Engineer at XPENG Motors, working on perception and behavior prediction for autonomous driving, and a research intern at Microsoft in 2021.
I received my Ph.D. in Electrical & Computer Engineering from the University of Washington in 2022, where I was a member of the Information Processing Lab (IPL), advised by Prof. Jenq-Neng Hwang. Earlier, I earned my M.S. in Electrical Engineering from Columbia University in 2018, where I was part of the DVMM Lab, advised by Prof. Shih-Fu Chang and Dr. Liangliang Cao.
News
-
Jan 2026
📄 New preprint A Unified 3D Object Perception Framework for Real-Time Outside-In Multi-Camera Systems is online. [arXiv]
-
Oct 2025
🎉 MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos is accepted to the ICCV 2025 Workshops. [Paper] [arXiv]
-
Jan 2025
🏆 Presented MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos at NVIDIA NTECH 2024 and received the Best Presentation Award.
-
Dec 2024
📄 New preprint MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos is online. [arXiv]
-
Oct 2024
🎉 Ego3DT: Tracking Every 3D Object in Ego-centric Videos is accepted by ACM Multimedia 2024. [arXiv] [DOI]
-
Jun 2024
🎤 Vision meets mmWave Radar: 3D Object Perception Benchmark for Autonomous Driving is presented at the IEEE Intelligent Vehicles Symposium (IV) 2024. [arXiv]
-
Dec 2023
🚀 Joined NVIDIA as a Senior Deep Learning Engineer, working on computer vision and deep learning for smart cities and smart spaces such as warehouses and factories.
-
Feb 2023
🚗 Joined XPENG Motors as a Senior Machine Learning Engineer, working on perception and behavior prediction for autonomous driving.
-
Jan 2023
🎉 Our paper Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking is published in IEEE Transactions on Multimedia (TMM). [arXiv]
-
Dec 2022
🎓 Successfully defended my Ph.D. thesis, Object 3D Perception via Camera-Radar Cross-Modality Learning for Autonomous Driving, at the University of Washington. [Thesis]
-
Nov 2021
🏁 Our challenge summary paper ROD2021 Challenge: A Summary for Radar Object Detection Challenge for Autonomous Driving Applications is presented at ACM ICMR 2021. [Paper] [Website]
-
Oct 2021
🥇 Won 1st place in both the MOTChallenge-STEP and KITTI-STEP tracks at the 6th BMTT Challenge, ICCV 2021. [Challenge]
-
Jul 2021
🎉 Our paper ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot is accepted by ICCV 2021. [PDF]
-
Jul 2021
🏆 Selected as a Qualcomm Innovation Fellowship (QIF) 2021 Finalist. [Link]
-
Jun 2021
🎤 Our paper Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment is presented at the Workshop on Autonomous Driving (WAD), CVPR 2021. [Paper] [Spotlight] [Poster] [WAD Full Video]
-
Jun 2021
💼 Started a research internship at Microsoft.
-
May 2021
🎉 Our paper Multi-Target Multi-Camera Tracking of Vehicles using Metadata-Aided Re-ID and Trajectory-Based Camera Link Model is accepted by IEEE Transactions on Image Processing (TIP). [IEEE] [arXiv]
-
Feb 2021
🎉 Our journal paper RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization is accepted by IEEE J-STSP. [IEEE] [arXiv]
-
Nov 2020
🎉 Our paper RODNet: Radar Object Detection Using Cross-Modal Supervision is accepted by WACV 2021. [PDF] [Code] [Dataset]
-
Aug 2020
🎉 Our paper Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model is accepted as Oral by ACM Multimedia 2020. [PDF]
-
Jun 2020
🥇 Won 1st place (Track 3) and runner-up (Track 2) at the 5th BMTT Challenge, CVPR 2020. [Challenge] [More]
-
Oct 2019
🎉 Our paper Monocular Visual Object 3D Localization in Road Scenes is accepted as a Long Oral at ACM Multimedia 2019. [Project] [Paper] [Video]
-
Oct 2019
🎉 Our paper TrackletNet (TNT): Multi-Object Tracking with TrackletNet is accepted as a Short Oral at ACM Multimedia 2019. [Paper] [Code]
-
Jun 2018
🎓 Started my Ph.D. at the University of Washington, advised by Prof. Jenq-Neng Hwang at the Information Processing Lab (IPL).
-
Feb 2018
🎓 Received my M.S. in Electrical Engineering from Columbia University.