Kun He | BUCS

Kun 

hk
Research Scientist, Facebook Reality Labs (Oculus Research)
Redmond, WA

firstname.lastname@oculus.com
Google Scholar

About

I am a research scientist in Facebook Reality Labs. Previously, I earned PhD (2018) and MSc (2013) in computer science from Boston University, advised by Professor Stan Sclaroff. My Bachelor's degree is from Zhejiang University.

I am interested in exploring solutions to computer vision problems using machine learning techniques, and I'm frequently attracted by the optimization aspect in such problems. My PhD dissertation focused on learning vector embeddings for high-dimensional visual data, which finds application in image retrieval and other related vision tasks.

During grad school, I did research internships with Leonid Sigal at Disney Research, and with Yan Lu at Honda Research Institute. I also worked with Pedro Felzenszwalb as a visiting student at Brown University.

News

Publications

Preprints

MIHash 

Hashing with Mutual Information [arXiv] [Code]
Kun He*, Fatih Cakir*, Sarah Adel Bargal, Stan Sclaroff
(* Equal contribution)

Journal Publications

ambiguous 

Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s) [Project page]
Danna Gurari, Kun He, Bo Xiong, Jianming Zhang, Mehrnoosh Sameki, Suyog Dutt Jain, Stan Sclaroff, Margrit Betke, Kristen Grauman
IJCV 2018

Conference Publications

Text2Clip 

Multilevel Language and Vision Integration for Text-to-Clip Retrieval [arXiv]
Huijuan Xu, Kun He, Bryan A. Plummer, Leonid Sigal, Stan Sclaroff, Kate Saenko
AAAI 2019 (accepted)

HBMP 

Hashing with Binary Matrix Pursuit [PDF] [Poster]
Fatih Cakir, Kun He, Stan Sclaroff
ECCV 2018

DOAP 

Local Descriptors Optimized for Average Precision [Project page]
Kun He, Yan Lu, Stan Sclaroff
CVPR 2018

TALR 

Hashing as Tie-Aware Learning to Rank [PDF] [Poster] [Code]
Kun He, Fatih Cakir, Sarah Adel Bargal, Stan Sclaroff
CVPR 2018

MIHash 

MIHash: Online Hashing with Mutual Information [PDF] [Poster] [Code]
Kun He*, Fatih Cakir*, Sarah Adel Bargal, Stan Sclaroff
(* Equal contribution)
ICCV 2017

eccv14 

Parameterizing Object Detectors in the Continuous Pose Space [PDF] [BibTeX] [Poster] [video]
Kun He, Leonid Sigal, Stan Sclaroff
ECCV 2014
[Tech report on implementation]

cvpr12 

Scale Resilient, Rotation Invariant Articulated Object Matching [PDF] [BibTeX]
Hao Jiang, Tai-Peng Tian, Kun He, Stan Sclaroff
CVPR 2012

Others

phdthesis 

Learning Deep Embeddings by Learning to Rank [PDF]
Kun He
Ph.D. dissertation, Boston University, 2018

G-MM 

Generalized Majorization-Minimization [arXiv]
Sobhan Naderi Parizi, Kun He, Stan Sclaroff, Pedro Felzenszwalb
Tech report

msthesis 

Stochastic Functional Descent for Learning Support Vector Machines [PDF]
Kun He
M.Sc. thesis, Boston University, 2013

Teaching

Misc