Chen Gao

iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
Chen Gao, Yuliang Zou, Jia-Bin Huang
Proceedings of The British Machine Vision Conference (BMVC), 2018
[Paper (PDF)]    [Project page]    [Code]    [Poster]

Panoramic Robust PCA for Foreground-Background Separation on Noisy, Free-Motion Camera Video
Chen Gao*, Brian E. Moore*, Raj Rao Nadakuditi
IEEE Transactions on Computational Imaging (TCI), 2019
[Paper (PDF)]    [Project page]    [Code]

Augmented Robust PCA For Foreground-Background Separation on Noisy, Moving Camera Video
Chen Gao, Brian E. Moore, Raj Rao Nadakuditi
Proceedings of IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2017 (Oral Presentation)
[Paper (PDF)]    [Project page]    [Code]    [Slides(video demo)]

Human-Object Interactions Detection
We tackle the challenging task of detecting human-object interactions (HOI). Our core idea is that the appearance of a person or an object instance contains informative cues on which relevant parts of an image to attend to for facilitating interaction prediction. To exploit these cues, we propose an instance-centric attention module that learns to dynamically highlight regions in an image conditioned on the appearance of each instance. Such an attention-based network allows us to selectively aggregate features relevant for recognizing HOIs.

Detecting Migrating Birds at Night
A vision-based system for detecting migrating birds in flight at night, which takes stereo videos of the night sky as inputs, detects multiple flying birds and estimates their orientations, speeds, and altitudes.

Foreground-Background Separation and Denoising on Noisy, Moving Camera Video
A robust PCA algorithm with total variation regularization for foreground-background separation and denoising on noisy, moving camera video. Our proposed algorithm registers the raw – possibly corrupted – frames of a video and then jointly processes the registered frames to produce a decomposition of the scene into a low-rank component that captures the static components of the scene, a smooth foreground component that captures the dynamic components of the scene, and a sparse component that can isolate corruptions and other non-idealities.

Virginia Tech
STAT5444 - Bayesian Statistics

University of Michigan
EECS442 - Computer Vision
EECS501 - Probability and Random Processes
EECS551 - Matrix Methods
EECS542 - Advanced Topics in Computer Vision
EECS545 - Machine Learning
EECS587 - Parallel Computing
EECS592 - Advanced Artificial Intelligence
EECS598 - Random Matrix Theory

Road Trip
I enjoy road trip as it's a great way to experience local customs and the spectacular landscape along the way reminds me how great our Creator is. One of my dream is to visit all the 59 national parks in the USA. I have visited 17 national parks already and am looking forward to my next journey. Here is a list of the national parks I've visited

Arches - Utah
Bryce Canyon - Utah
Canyonlands - Utah
Capitol Reef - Utah
Crater Lake - Oregon
Everglades - Florida
Grand Canyon - Arizona
Grand Teton - Wyoming
Great Sand Dunes - Colorado
Joshua Tree - California
Kings Canyon - California
Mesa Verde - Colorado
Sequoia - California
Shenandoah - Virginia
Yellowstone - Wyoming, Montana, Idaho
Yosemite - California
Zion - Utah

Painting
I spent 6 years learning figure sketch, traditional Chinese painting and Gongbi, specialized in Bird-and-flower painting. Through painting I find inner peace.

Big fan of Rubik's Cube
4x4x4
5x5x5

Tennis lover
#tennislover

The Mighty
Humble yourselves, therefore, under the mighty hand of God so that at the proper time he may exalt you, casting all your anxieties on him, because he cares for you.                                                                       1 Peter 5: 6-7