Mingze Xu

Mingze Xu

徐 铭 泽


Ph.D. Candidate

School of Informatics, Computing, and Engineering

Indiana University


IU Computer Vision Lab

611 N Park Ave

Bloomington, IN 47408

mx6 [at] indiana [dot] edu


[Research] [Publications] [Projects] [Teaching] [CV]

News

  • 11/2017:   Successfully acquire Ph.D. candidacy at Indiana University.

  • 09/2017:   Two papers accepted by Round 1 of WACV 2018.

  • 05/2017:   One paper accepted by ICIP 2017.

  • 05/2017:   Start my research internship at Midea CRC.

  • 02/2017:   One paper accepted by CVPR 2017.

  • 08/2015:   Start my research career at Indiana University.

Research

Hi, I'm Mingze. I am a third-year Ph.D. candidate of School of Informatics, Computing, and Engineering at Indiana University. I received a Master degree in Computer Science from Indiana University (2014) and a Bachelor degree in Software Engineering from Jilin University (2012). I am advised by Prof. David Crandall.

My research is primarily in the area of Computer Vision and Deep Learning. In particular, I focus on applying deep neural networks to recognition tasks in videos, which improves the performance of object detection and segmentation close to that of human. I am also working on understanding large-scale data from Polar Science, such as 3D object segmentation and reconstruction from sequential tomograms.

Publications

  • Mingze Xu, Chenyou Fan, John Paden, Geoffrey Fox, and David Crandall. Multi-Task Spatiotemporal Neural Networks for Structured Surface Reconstruction. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.  (Round 1, 30.0% acceptance rate).  [pdf] [bibtek]

  • Mingze Xu, Aidean Sharghi, Xin Chen, and David Crandall. Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.  (Round 1, 30.0% acceptance rate).  [pdf] [bibtek]

  • Mingze Xu, David Crandall, Geoffrey Fox, and John Paden. Automatic Estimation of Ice Bottom Surfaces from Radar Imagery. In IEEE International Conference on Image Processing (ICIP), 2017. (Oral, 45.0% acceptance rate).  [pdf] [bibtek]

  • Chenyou Fan, Jangwon Lee, Mingze Xu, Krishna Kumar Singh, Yong Jae Lee, David Crandall, and Michael Ryoo. Identifying First-person Camera Wearers in Third-person Videos. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.  (Poster, 29.0% acceptance rate).  [pdf] [bibtek]

Teaching

  • Fall 2017: Undergraduate Research Opportunities in Computing

  • Spring 2017: Undergraduate Research Opportunities in Computing

  • Fall 2014: CSCI B351 Introduction to Artificial Intelligence

  • Spring 2014: CSCI B552 Knowledge Based Artificial Intelligence

Last update: 12/31/2017