Edward Hsiao

profile 

Edward Hsiao
Ph.D. Student
Robotics Institute
Carnegie Mellon University

Advisor: Martial Hebert

Contact

Smith Hall 201, Robotics Institute
Carnegie Mellon University
5000 Forbes Ave
Pittsburgh, PA 15213

Email: ehsiao [at] cs [dot] cmu [dot] edu

Biography

I am currently a Ph.D. student in the Robotics Institute at Carnegie Mellon University. My research interests are in Computer Vision and Machine Learning, specifically the problem of object recognition. My advisor at the Robotics Institute is Dr. Martial Hebert. Before coming to Carnegie Mellon University, I did my undergratuate studies at the California Institute of Technology where I was advised by Dr. Pietro Perona.

Projects

profile 

Gradient Networks: Explicit Shape Matching Without Extracting Edges
Edward Hsiao and Martial Hebert

profile 

Occlusion Reasoning for Object Detection under Arbitrary Viewpoint
Edward Hsiao and Martial Hebert

profile 

Addressing Feature Ambiguity for Point-Based 3D Object Recognition
Edward Hsiao, Alvaro Collet and Martial Hebert

Publications

Occlusion reasoning for object detection under arbitrary viewpoint
E. Hsiao and M. Hebert
PAMI, 2014.
[preprint pdf][bibtex]

Car make and model recognition using 3D curve alignment
K. Ramnath, S. Sinha, R. Szeliski and E. Hsiao
In WACV, 2014.
[pdf][bibtex]

Coherent occlusion reasoning for instance recognition
E. Hsiao and M. Hebert
In ACPR, 2013.
[pdf][bibtex]

Addressing ambiguity in object instance detection
E. Hsiao
Doctoral thesis, Carnegie Mellon University, 2013.
Advisor: Martial Hebert
[pdf][bibtex]

Gradient networks: Explicit shape matching without extracting edges
E. Hsiao and M. Hebert
In AAAI, 2013. (oral)
[pdf][bibtex]

Shape-based instance detection under arbitrary viewpoint
E. Hsiao and M. Hebert
Book chapter in Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective, Springer, 2013.
Editors: Sven Dickinson and Zygmunt Pizlo
[pdf][bibtex]

Occlusion reasoning for object detection under arbitrary viewpoint
E. Hsiao and M. Hebert
In CVPR, 2012.
[pdf][dataset][bibtex]

Making specific features less discriminative to improve point-based 3D object recognition
E. Hsiao, A. Collet and M. Hebert
In CVPR, 2010.
[pdf][dataset][bibtex]

Automatic behavior analysis of epileptic seizures in mice
E. Hsiao
Bachelor thesis, California Institute of Technology, 2008.
Advisor: Pietro Perona

An optical tweezer actuated, nanoaperture grid-based optofluidic microscope implementation method
X. Heng, E. Hsiao, D. Psaltis and C. Yang.
Optics Express, 2007.
[pdf][bibtex]

A high-resolution optofluidic microscope with optical tweezer actuation
X. Heng, E. Hsiao, D. Psaltis and C. Yang
Proceedings of SPIE, 2007.

Patents

Object identification using 3-D curve matching
E. Hsiao, R. Szeliski, S. Sinha, K. Ramnath, C. Zitnick, and S. Baker
U.S. Patent filed December 2011.

Specific Object Recognition Datasets

Links

Random