SVCL - Pei Wang

Home People Research Publications Demos

News Jobs Prospective
Students About Internal

Pei Wang
Department of Electrical and Computer Engineering,
University of California, San Diego
9500 Gilman Drive, Mail code 0409
La Jolla, CA 92093-0409

EBU 1, Room 4606

Email: pew062@ucsd.edu
Phone: (858) 729-8480
[CV]

Bio:

Now, I am a second-year Ph.D. student advised by professor Nuno Vasconcelos, working on machine learning, deep learning and their applications on computer vision. Before this, I got my bachelor degree from University of Electronic Science and Technology of China (UESTC) in 2014 and master degree from National Laboratory of Pattern Recognition (NLPR) advised by professor Weiming Hu and Chunfeng Yuan in 2017.

Research:

My current research lies on a new interesting direction, realistic predictors. Specifically, these predictors are aimed to let the predictors be self-assess, refuse hard tasks and guarantee a target good performance on non-rejected easy ones. I'm also interested in other related problems, learning to reject, selective classification, confidence score calibration, out-of-distribution detection, uncertainty estimation/qualifying, error prediction, etc.

My online publication profile can be found at Google Scholar.

Representative Publications:

Towards Realistic Predictors
Pei Wang and Nuno Vasconcelos
European Conference on Computer Vision (ECCV)
Munich, Germany, 2018 (Oral presentation)
[ project | ps | pdf | BibTex ]

Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition
Pei Wang, Chunfeng Yuan, Weiming Hu, Bing Li and Yanning Zhang
European Conference on Computer Vision (ECCV)
Amsterdam, the Netherlands, 2016
[ project | ps | pdf | BibTex ]

Awards:

UCSD ECE department FellowShip, Sep 2017

National Scholarship, Nov 2013

National Scholarship, Nov 2012

Last update: Dec, 2018

Home	People	Research	Publications	Demos

News	Jobs	Prospective Students	About	Internal

Bio:
Now, I am a second-year Ph.D. student advised by professor Nuno Vasconcelos, working on machine learning, deep learning and their applications on computer vision. Before this, I got my bachelor degree from University of Electronic Science and Technology of China (UESTC) in 2014 and master degree from National Laboratory of Pattern Recognition (NLPR) advised by professor Weiming Hu and Chunfeng Yuan in 2017.
Research:
My current research lies on a new interesting direction, realistic predictors. Specifically, these predictors are aimed to let the predictors be self-assess, refuse hard tasks and guarantee a target good performance on non-rejected easy ones. I'm also interested in other related problems, learning to reject, selective classification, confidence score calibration, out-of-distribution detection, uncertainty estimation/qualifying, error prediction, etc.
My online publication profile can be found at Google Scholar.
Representative Publications:
	Towards Realistic Predictors Pei Wang and Nuno Vasconcelos European Conference on Computer Vision (ECCV) Munich, Germany, 2018 (Oral presentation) [ project \| ps \| pdf \| BibTex ]
	Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition Pei Wang, Chunfeng Yuan, Weiming Hu, Bing Li and Yanning Zhang European Conference on Computer Vision (ECCV) Amsterdam, the Netherlands, 2016 [ project \| ps \| pdf \| BibTex ]
Awards:
UCSD ECE department FellowShip, Sep 2017 National Scholarship, Nov 2013 National Scholarship, Nov 2012
Last update: Dec, 2018