Email: hongtengxu313@gmail.com

Hongteng Xu (许洪腾)


I am a Ph.D. student in the School of Electrical and Computer Engineering, Georgia Tech, jointly supervised by Prof. Hongyuan Zha (CSE) and Prof. Mark A. Davenport (ECE). At the same time, I am a research assistant in the College of Computing at Georgia Tech. I received my Bachelor Degree in Electronic and Information Engineering from Tianjin University in 2010 and my dual Master Degree in ECE from Shanghai Jiao Tong University and Georgia Tech in 2013. My research interests include machine learning and its applications, e.g., computer vision and data mining. 

News: 
05/12/2017: Our paper "Learning Hawkes Processes from Short Doubly-Censored Event Sequences" has been accepted via ICML 2017!
04/10/2017: Our paper "Personalized Key Frame Recommendation" has been accepted via SIGIR 2017!
03/17/2017: A subset of our IPTV user behavior data has been released!
03/17/2017: The demo code of our paper "A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering" has been released!
03/17/2017: The demo code and partial data of our CVPR17 paper "Fractal Dimensional Invariant Filtering and Its CNN-based Implementation" have been released!
03/03/2017: Our paper "Fractal Dimension Invariant Filtering and Its CNN-based Implementation" has been accepted via CVPR 2017!
02/15/2017: I gave a poster introduction about "Learning Granger Causality for Hawkes Processes" on 2017 Information Theory and Applications Workshop (2017 ITA).
01/23/2017: I gave a talk about "Point Processes and Their Applications" in Louisiana State University.
12/20/2017: I entered Baidu PhD Fellowship Finalist.
12/19/2016: I gave a talk about "Point Processes and Their Applications" in the Institute of Image Communication and Information Processing, Shanghai Jiao Tong University.
10/15/2016: Our paper "Patient Flow Prediction via Discriminative Learning of Mutually-Correcting Processes" has been accepted via IEEE Trans. on Knowledge and Data Engineering (TKDE)!
07/13/2016: The bugs of the demo code of our ICML16 paper "Learning Granger Causality for Hawkes Processes" have been fixed! Thanks Julia Proskurnia's feedback!
06/23/2016: The demo code of our ICML16 paper "Learning Granger Causality for Hawkes Processes" has been released!
06/23/2016: The demo code of our IJCAI15 paper "Multi-task Multi-dimensional Hawkes Processes for Modeling Event Sequences" has been released!
04/25/2016: Our paper "Learning Granger Causality for Hawkes Processes" has been accepted via ICML 2016!
01/15/2016: Our paper "Learning Mixtures of Markov Chains from Aggregate Data with Structural Constraints" has been accepted via IEEE Trans. on Knowledge and Data Engineering (TKDE)!
10/04/2015: The demo code of our ICCV15 paper "Unsupervised Trajectory Clustering via Adaptive Multi-Kernel-based Shrinkage" has been released!
09/15/2015: The code of our TIP15 paper "Vector Sparse Representation of Color Image Using Quaternion Matrix Analysis" has been released!

Recent Honor:
Travel award of ICML, 2016
Invited presentation on ICRA2015 for my work ``Active Manifold Learning via Gershgorin Circle Guided Sample Selection'', 2015
Outstanding Master Thesis of Shanghai, 2014
1/3 Courlter Fellowship, Georgia Tech, 2010

Recent Professional Activities:
Reviewer for NIPS2015, AAAI2017, AISTATS2015-2017, IEEE Trans. on Multimedia, JVIS, Neurocomputing, MULT. 
Invited Speaker of ICRA2015 (introduce my AAAI2015 work "Active Manifold Learning via Gershgorin Circle Guided Sample Selection
").