images/avatar3.jpg

Hou-Ning Hu

M.S. student, Vision Science Lab
National Tsing Hua University, Taiwan

I am currently an Electrical Engineering graduate student at the Vision Science Lab of National Tsing Hua University, working with Prof. Min Sun.
My research focuses on Deep Learning and its applications in Computer Vision. In particular, I now dig deep into a combination of deep neural network and virtual reality.

NEWS: Our paper accepted to CVPR 2017 as oral presentation!

Publications

2017

Hou-Ning Hu*, Yen-Chen Lin*, Ming-Yu Liu, Hsien-Tzu Cheng, Yung-Ju Chang, and Min Sun
Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Videos
IEEE CVPR 2017 Oral
(* indicates equal contribution)
[BibTex]    [PDF (High Resolution)]    [PDF (ArXiv)]    [Project Page]   

@inproceedings{HuCVPR17,
author = {Hou-Ning Hu and Yen-Chen Lin and Ming-Yu Liu and Hsien-Tzu Cheng and Yung-Ju Chang and Min Sun},
title = {Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Videos},
journal = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2017}
}

Yen-Chen Lin, Yung-Ju Chang, Hou-Ning Hu, Hsien-Tzu Cheng, Chi-Wen Huang, and Min Sun
Tell Me Where to Look: Investigating Ways for Assisting Focus in 360° Video
ACM CHI 2017
[BibTex]    [PDF (High Resolution)]    [PDF (DOI)]    [Project Page]   

@inproceedings{LinCHI17,
author = {Lin, Yen-Chen and Chang, Yung-Ju and Hu, Hou-Ning and Cheng, Hsien-Tzu and Huang, Chi-Wen and Sun, Min},
title = {Tell Me Where to Look: Investigating Ways for Assisting Focus in 360° Video},
booktitle = {Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems},
series = {CHI '17},
year = {2017},
isbn = {978-1-4503-4655-9},
location = {Denver, Colorado, USA},
pages = {2535--2545},
numpages = {11},
url = {http://doi.acm.org/10.1145/3025453.3025757},
doi = {10.1145/3025453.3025757},
acmid = {3025757},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {360-degree videos, auto pilot, focus assistance, video experience, visual guidance},
}

Side Projects

Tensorflow implementation of SoundNet

A Tensorflow implementation of SoundNet from the paper "SoundNet: Learning Sound Representations from Unlabeled Video" by Yusuf Aytar, Carl Vondrick, Antonio Torralba. NIPS 2016

Experiences

Vision Science Lab

Advisor: Prof. Min Sun Graduate student
Jul. 2015 - Present
Computer Vision and Deep Learning.


EE6485 Computer Vision

Teaching assistant
Sep. 2016 - Jan. 2017

Resume

Open it up!

Last update: March 2017

Contact

Address:
Vision Science Laboratory
No. 101, Section 2, Kuang-Fu Road,
Hsinchu, Taiwan 30013

Office: EECS 711
E-mail: eborboihuc[at]gmail[dot]tw