Manh Huynh


CEAS PhD Candidate
Department of Computer Science and Engineering
College of Engineering and Applied Science
University of Colorado Denver
Email: huynh.manh@ucdenver.edu
Phone: 720-209-0140.
Address: LW827, 1380 Lawrence Street, Denver 80217, CO, US

Bio

I'm currently working as lab/research assistant in Parallel and Distributed Lab (PDS) , under supervision of Professor Gita Alagband. My research interests includes computer vision, machine learning and parallel distributed computing.

Quotes of my life:
"Anyone who has never made a mistake has never tried anything new." Albert Einstein.

Research

RNN-based motion prediction models in Online Multi-target Tracking [in progress]

Spatiotemporal KSVD Dictionary Learning for Online Multi-target Tracking [under submission]

In this project, we present a new spatiotemporal discriminative KSVD dictionary algorithm (STKSVD) for learning target appearance in online multi-target tracking system. We characterize the spatial and temporal information between target’s samples through a new STKVSD appearance learning algorithm to better discriminate targets. Our method is derived from the original K Singular Value Decomposition (KSVD) dictionary learning algorithm, a successful method in image reconstruction that minimizes signal reconstruction error.

Machine learning based Mobile Devices Identification
We apply machine learning techniques for a mobile device identification by using capacitive signals (emits from mobile screens) as input signals. The method relies on a key observation that each capacitive touch screen has a unique capacitive signature which are caused by either the difference in touch sensing technologies or the imperfections of the sensor during its fabrication.
Saliency Based based Image Segmentation
Salient object detection is a one of the challenging task in object segmentation and recognition. We present an efficient and simple saliency detection method using Gaussian Mixture Modeling and Tensor voting. The color saliency and spatial saliency are measured by using the color distinctiveness and spatial distribution. The final saliency map is finally generated by fusing color saliency map and spatial saliency map.

Publications

Small Object Segmentation Based on Visual Saliency in Natural Images
Huynh Trung Manh, GueeSang Lee
Journal of Information Processing System (JIPS), 2013

Effiecient Saliency Detection from Joint Spatial and Color Cues
Huynh Trung Manh, GueeSang Lee
The 2nd International Conference of Smart Media and Application, Vol.2, No.1, pp 286-293, Malaysia, 2013.

Saliency Detection by Tensor Voting based Gaussian Modeling
Huynh Trung Manh, GueeSang Lee
Proceedings of International Conference on Ubiquitous Information Management and Communication (IMCOM 2015), Bali, Indonesia, January 8-10, 2015..

Academic Experiences

Teaching CSCI 1411 Fundamentals of Computing Lab (Summer 2017)
Teaching CSCI 1510 Logic Design (2015-Present)
Teaching Assistant CSCI 7751 Paralel Distribued System (Fall 2017)
Teaching Assistant CSCI 5593 Advanced Computer Architecture (2015-Present)
Teaching Assistant CSCI 5800 Computer Storage System (Summer 2016)
Teaching Assistant CSCI 4761 Intro to Computer Networks (Spring 2015)
Teaching Assistant CSCI 3412 Principles of Programming Langugues (Fall 2016)

Honors & Awards

Tashiro Tutoring Award (2016-2017), University of Colorado Denver, US.
DataLogic Scanning Engineering Scholarship (2011)

Graduate Coursework

CSCI 5593: Advanced Computer Architecture (Spring 2015)
CSCI 5451: Advanced Algorithms (Fall 2015)
CSCI 7800: Special Topics (Fall 2015)
CSCI 7551: Parallel Distributed System (Fall 2016)

Home Remedies For Wrinkles
Count Stats Visits