Yi-Hsuan Tsai

Email: ytsai [at] nec-labs [dot] com

Office: 10080 N. Wolfe Rd. Suite SW3-350, Cupertino, CA 95014

I am a researcher at NEC Laboratories America. Please contact me if you are interested in doing a research internship.

Biography

I received my Ph.D in the Department of Electrical Engineering and Computer Science at University of California, Merced in 2017 advised by Prof. Ming-Hsuan Yang in the Vision and Learning Lab. Before coming to UC Merced in 2012, I received my M.S. degree in the Department of Electrical Engineering and Computer Science from University of Michigan, Ann Arbor in 2012, and my B.S. degree in the Department of Electronics Engineering from National Chiao-Tung University, Hsinchu, Taiwan in 2009.

My CV and Google Scholar

Research Interest

Semantic Segmentation, Video Understanding, Representation Learning, Domain Adaptation

Full Publication List

News & Events

  • NEW 02/2019: I will serve as an Area Chair for AVSS'19.
  • NEW 01/2019: One ICRA'19 paper on sparse depth reconstruction is accepted [Project Page].
  • NEW 01/2019: Check our new paper on domain adaptation for structured output [Paper].
  • NEW 12/2018: Our ACCV'18 paper receives the Best Student Paper Honorable Mention!
  • NEW 09/2018: One ACCV'18 paper on "transfer learning for unseen object segmentation" is accepted as oral [Project Page].
  • NEW 07/2018: One BMVC'18 paper on semi-supervised semantic segmentation is accepted [Project Page].
  • NEW 06/2018: Receive CVPR'18 Outstanding Reviewer Award.
  • NEW 04/2018: Give a talk on "learning cross-domain tasks" at National Tsing-Hua University.
  • NEW 02/2018: Two spotlight papers are accepted in CVPR'18 on Domain Adaptation [Code] and Video Object Segmentation [Code].
  • 12/2017: Give two talks at Academia Sinica and National Taiwan University [Abstract].
  • 12/2017: Our Vehicle Rear Signal Dataset is released.
  • 11/2017: One AAAI'18 paper on "learning binary representations for video streaming" is accepted [Project Page] [Blog].
  • 10/2017: One WACV'18 paper on "learning to generate video-story" is accepted [PDF].
  • 10/2017: Receive ICCV'17 Outstanding Reviewer Award.
  • 10/2017: Our team won the 3rd place in the VisDA Segmentation Challenge in ICCV'17 workshop!
  • 08/2017: Successfully defended my PhD!
  • 07/2017: Two papers are accepted in ICCV'17 on Video Object Segmentation [Code] and Scene Parsing [Code].
  • 07/2017: Our result on 2017 DAVIS Challenge is accepted to present in CVPR'17 workshop [code].
  • 02/2017: One CVPR'17 paper on end-to-end image harmonization is accepted [demo code].
  • 02/2017: Start my research internship at NVIDIA Research (Santa Clara) in the Visual Computing team!
  • 11/2016: Check the demo of our SIGGRAPH'16 paper at Adobe MAX 2016 Sneak Peeks!
  • 10/2016: Check our results (CVPR'16 paper) on the DAVIS benchmark dataset.
  • 10/2016: Receive ECCV'16 Outstanding Reviewer Award.
  • 08/2016: Receive Graduate Dean's Dissertation Fellowship!
  • 08/2016: One ACCV'16 paper on video scene parsing is accepted as oral.
  • 07/2016: One ECCV'16 paper on video object co-segmentation is accepted.
  • 06/2016: Start my second research internship at Adobe Research (San Jose)!
  • 03/2016: Receive CVPR'16 Doctoral Consortium Travel Award.
  • 03/2016: One SIGGRAPH'16 paper is conditionally accepted!
  • 03/2016: One CVPR'16 paper on video object segmentation is accepted as spotlight.
  • 05/2015: Start my research internship at Adobe Research (San Jose), working with Dr. Xiaohui Shen, Dr. Zhe Lin and Dr. Kalyan Sunkavalli.
  • 03/2015: One CVPR'15 paper is accepted.
  • 06/2014: Start my internship in the Department of Perceiving Systems at Max Planck Institute for Intelligent Systems with Prof. Michael J. Black.
  • 05/2014: One ICIP'14 paper is accepted.
  • 09/2013: One ICCV'13 paper is accepted.
  • 07/2013: One BMVC'13 paper is accepted.
  • 05/2013: Start my research internship at Qualcomm Research Center (San Diego), working with Dr. Onur Hamsici.