Mingze Xu

Mingze Xu

徐 铭 泽

Applied Scientist at AWS AI

Amazon Nitro North

2250 7th Ave

Seattle, WA 98121

xumingze0308 [at] gmail [dot] com


  • 11/2021:   [New] We release the code of LSTR!

  • 09/2021:   [New] One paper accepted to NeurIPS 2021 as Spotlight!

  • 07/2021:   [New] One paper accepted to ICCV 2021 as Oral!

  • 07/2021:   [New] We release LSTR, a more effective and efficient method for modeling prolonged sequence data! LSTR achieves SoTA on Online Action Detection benchmarks!

  • 05/2021:   Our team won the 3rd place in the Second nuScenes Prediction Challenge at ICRA 2021.

  • 03/2021:   One paper accepted to ICME 2021 as Oral!

  • 04/2020:   We release our Detection of Traffic Anomaly (DoTA) dataset!

[New] If you are interested in internship opportunities (Spring/Summer/Fall 2022) in our team, please feel free to send me an email with your resume.


Hi, I'm Mingze. I'm an Applied Scientist at AWS AI in Seattle.

I received my Ph.D. degree in Computer Science from Indiana University, advised by Prof. David Crandall in 2020. I was a visiting student researcher at Georgia Institute of Technology, working with Prof. Dhruv Batra and Prof. Devi Parikh, in 2018. Before that, I received my Master's degree in Computer Science from Indiana University and my Bachelor's degree in Software Engineering from Jilin University.

My research interests lie primarily in the area of computer vision and deep learning. In particular, my recent and ongoing projects consider following applications:

  • Action and activity recognition

  • First-person (egocentric) vision

  • Person tracking and re-identification

  • Multimodal learning

  • Facial recognition

Selected Publications

Please also see my publications at Google Scholar for a complete list.

Teaching Experience

Research Mentor

  • Fall 2017: Undergraduate Research Opportunities in Computing

  • Spring 2017: Undergraduate Research Opportunities in Computing

Associate Instructor

  • Fall 2014: CSCI B351 Introduction to Artificial Intelligence

  • Spring 2014: CSCI B552 Knowledge Based Artificial Intelligence


Conference Program Committee or Reviewer

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019, 2020, 2021, 2022)

  • IEEE International Conference on Computer Vision (ICCV 2019, 2021)

  • European Conference on Computer Vision (ECCV 2020)

  • Conference on Neural Information Processing Systems (NeurIPS 2020, 2021)

  • International Conference on Learning Representations (ICLR 2020, 2021)

  • AAAI Conference on Artificial Intelligence (AAAI 2020)

  • International Joint Conference on Artificial Intelligence (IJCAI 2020)

  • IEEE International Conference on Robotics and Automation (ICRA 2020)

  • IEEE Winter Conference on Applications of Computer Vision (WACV 2019, 2020, 2021)

Journal Reviewer

  • IEEE Transactions on Image Processing (TIP)

  • IEEE Transactions on Multimedia (MM)

  • Journal of Visual Communication and Image Representation (JVCIR)

Last update: 11/18/2021