Joe Yue-Hei Ng


Bio

I obtained my PhD in the Department of Computer Science at University of Maryland, College Park, with Prof. Larry Davis as my supervisor. Before coming to UMD, I got my Bachelor degree in Computer Science from The Chinese University of Hong Kong. My research has been primarily focused on computer vision, specifically video action recognition.


Publications

ActionFlowNet: Learning Motion Representation for Action Recognition

Joe Yue-Hei Ng, Jonghyun Choi, Jan Neumann, Larry S. Davis

In IEEE Winter Conference on Applications of Computer Vision (WACV) 2018

Ref: [arxiv]

Temporal Difference Networks for Video Action Recognition

Joe Yue-Hei Ng, Larry S. Davis

In IEEE Winter Conference on Applications of Computer Vision (WACV) 2018

Ref: [paper]

FASON: First And Second Order Information Fusion Network for Texture Recognition

Xiyang Dai, Joe Yue-Hei Ng and Larry S. Davis

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

Ref: [pdf]

Generating Holistic 3D Scene Abstractions for Text-based Image Retrieval

Ang Li, Jin Sun, Joe Yue-Hei Ng, Ruichi Yu, Vlad I. Morariu and Larry S. Davis

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

Ref: [arxiv]

Beyond Short Snippets: Deep Networks for Video Classification

Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga and George Toderici

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015

Ref: [arxiv], [Google research blog]

Exploiting Local Features from Deep Networks for Image Retrieval

Joe Yue-Hei Ng, Fan Yang and Larry S. Davis

In IEEE Conference on Computer Vision and Pattern Recognition, DeepVision Workshop (CVPRW) 2015

Ref: [arxiv]


Internship Experience

2017

Salesforce Research

Summer intern
2016

Qualcomm Research, Amsterdam

Summer intern
2016

Comcast Lab

Part-time intern
2015

Google Research

Summer intern
2014

Google Research

Summer intern
2012

Raytheon, BBN Technologies

Summer Intern

Talks

June 2016

University of Amsterdam, Netherlands

Beyond Short Snippets: Deep Networks for Video Classification (Invited Talk)
May 2017

Mid-Atalantic Computer Vision (MACV) Workshop, University of Pennsylvania

ActionFlowNet: Learning Motion Representation for Action Recognition
Mar 2018

Workshop on Computer Vision for Active and Assisted Living, WACV 2018

ActionFlowNet: Learning Motion Representation for Action Recognition (Invited Talk)