Trinh, Hoang

(Vietnamese name: Trịnh Nguyên Hoàng)

PhD in Computer Science


About me: I am currently a lead applied researcher at Ebay Inc, applying machine learning, data science and AI to bringing better e-comerce experience to customers. Prior to that, I was data science team lead and senior data scientist at Misfit, focusing on gaining insights into users' activeness and healthiness, from multi-sensor data as well as their derived data, using signal processing, machine learning, statistics and data analysis techniques. I had previously been with UtopiaCompression, and IBM Research T. J. Watson, building multiple real-world machine learning and computer vision systems.

My PhD thesis, under the supervision of Prof. David McAllester, introduced a general machine learning approach called Unsupervised CRF learning based on maximizing the conditional likelihood, with application to computer vision systems that recover the 3-D scene geometry from images.

Research interests: Machine learning, Data science, AI, Computer Vision, NLP, and Robotics

Profile: LinkedIn

Updates | Research | Contact

Research Publications and Projects:

Unsupervised Learning of Stereo Vision with Monocular Cues.
(with David McAllester)
BMVC 2009.

This paper was part of a talk given by Prof. David McAllester at MLSS'09.
In this paper we used a modified version of the Stanford Stereo Dataset. You can click to download our training data and the testing data .
Hand Tracking by Binary Quadratic Programming.
H. Trinh, Q. Fan, P. Gabbur, S. Pankanti.
CVPR 2012.
Detecting Human Activities in Retail Surveillance Using Hierarchical Finite State Machine.
H. Trinh, Q. Fan, S. Pankanti et al.
ICASSP 2011.
Enhanced Rail Component Detection and Consolidation for Rail Track Inspection.
H. Trinh, Y. Li, N. Haas, C. Otto, S. Pankanti.
WACV 2012.
Saliency-based UAV Video Event Detection and Summarization.
H. Trinh, J. Li, S. Pankanti.
ICPR 2012.
Multimodal Ranking for Non-Compliance Detection in Retail Surveillance.
H. Trinh, S. Pankanti, Q. Fan.
WACV 2012 (oral).
Human face and facial parts detection and segmentation.
FlashFoto project.
A Machine Learning Approach to Recovery of Scene Geometry from Images.
PhD Thesis, July 2010.

Structure and Motion from Road-Driving Stereo Sequences.
IEEE Workshop on 3D Information Extraction for Video Analysis and Mining - CVPR 2010.

Video 1: The road-driving sequence
Video 2: The depth map
Video 3: Road and sky detection
Video 4: 3D scene reconstruction
Stereo Pair Training of Monocular Depth Estimation.
Efficient Stereo Algorithm using Multiscale Belief Propagation on Segmented Images.
BMVC 2008.
Particle-based Belief Propagation for Structure from Motion and Dense Stereo Vision with unknown camera constraints.
(with David McAllester)
2nd Robot Vision Workshop, Proceedings. LNCS 4931 Springer 2008, ISBN 978-3-540-78156-1.


ntrinh at ttic dot edu

eXTReMe Tracker