Profile Image

Jin Sun

Postdoctoral Associate

2 W Loop Rd, New York, NY 10044

jinsun AT

Research Interests

My research focus in computer vision has been object recognition and scene understanding in general. In particular, I'm working on learning the complex interactions between objects: e.g., geometrical and contextual.

At the same time, I'm interested in not only solving standard vision problems with deep neural networks (e.g., object detection using CNNs) but also understanding the characteristics of their structures (e.g., what visual representation does a network compute?).

I'm also interested in applying computer vision in applications such as Human Computer Interactions to improve people's quality of life.


I'm currently a Postdoctoral Associate at Cornell Tech, working with Prof. Noah Snavely. I received my PhD degree in Computer Science from the University of Maryland. My PhD advisor is Prof. David Jacobs.

Previously I was in a 3+2 program where I received a Master's degree in Computer and Information Science from Temple University and my Bachelor's degree in Automation from the University of Science and Technology of China (USTC). My advisor in Temple was Prof. Haibin Ling.

I graduated in 2005 from the High School Affiliated to Renmin University of China (RDFZ).

Selected Publications

Topic Keywords:

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
Hao Zhou*, Jin Sun*, Yaser Yacoob, David Jacobs
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Utah, United States, 2018 (Spotlight Presentation). [Arxiv]

Seeing What Is Not There: Learning Context to Determine Where Objects Are Missing
Jin Sun and David Jacobs
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, United States, 2017 (Spotlight Presentation). [Arxiv]

Generate Holistic 3D Scene Abstractions for Text-based Image Retrieval
Ang Li, Jin Sun, Joe Yue-Hei Ng, Ruichi Yu, Vlad I. Morariu, Larry S. Davis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, United States, 2017. [Arxiv]

Tohme: Detecting Curb Ramps in Google Street View Using Crowdsourcing, Computer Vision, and Machine Learning
Kotaro Hara, Jin Sun, Robert Moore, David Jacobs, Jon Froehlich
27th ACM Symposium on User Interface Software and Technology (UIST), Hawaii, United States, 2014. [PDF]

Scale and Object Aware Image Thumbnailing
Jin Sun and Haibin Ling
International Journal of Computer Vision (IJCV), 2013. [PDF],[Code],[Dataset]

Scale and Object Aware Image Retargeting for Thumbnail Browsing
Jin Sun and Haibin Ling
13th IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011. [PDF]

Object Category Classification Using Occluding Contours
Jin Sun, Christopher Thorpe, Nianhua Xie, Jingyi Yu, and Haibin Ling
6th International Symposium on Visual Computing (ISVC), Las Vegas, United States, 2010. Oral Presentation. [PDF], [Dataset (DT-OC5)]