Björn Stenger

Group Leader, Lead Scientist
Rakuten Institute of Technology (RIT)

E-mail         Scholar         Full Publication List

About

Vision program leader & researcher at the Rakuten Institute of Technology.

Our team works on core AI algorithms and applications.

Interests: Machine learning applied to computer vision, video processing and generative design.

[prior work]

News

2020/06 - CVPR WS Biometrics paper: Seamless Payment System Using Face and Low-Energy Bluetooth (upcoming)

2020/06 - CVPR paper: Deblurring by Realistic Blurring (upcoming)

2020/04 - CHI paper: EMI: An Expressive Mobile Interactive Robot

2020/04 - Welcome to Jose Carranza (Costa Rica Institute of Technology, INRIA)

2019/11 - ICCV workshop paper: 3D Hand Pose Estimation from RGB Using Privileged Learning with Depth Data

2019/04 - Welcome to Mijung Kim (Yonsei U, Stony Brook U, Ghent U)

2019/09 - Welcome to M Rasyid Aqmar (IT Bandung, Tokyo Tech, Osaka U))

2019/08 - Paper accepted at ICDM 2019: Learning Classifiers on Positive and Unlabeled Data with Policy Gradient

Projects

3D Hand Pose Estimation from RGB Using Privileged Learning with Depth Data
S. Yuan, B. Stenger, T.-K.Kim
ICCV Workshop: Observing and Understanding Hands in Action, November 2019.

A method for accurate RGB hand pose estimation, with privileged learning on large depth data (BigHand2.2M).

[bibtex]
@InProceedings{YuanICCVHands2019,
author =    {Yuan, S. and Stenger, B. and Kim, T.-K.},
title =     {3D Hand Pose Estimation from RGB Using Privileged Learning 
             with Depth Data},
booktitle = {ICCV Workshop: Observing and Understanding Hands in Action},
year =      {2019},
month =     {November}
}
Learning Classifiers on Positive and Unlabeled Data with Policy Gradient
T. Li, C.-C. Wang, Y. Ma, P. Ortal, Q. Zhao, B. Stenger, Y. Hirate.
IEEE International Conference on Data Mining (ICDM), November 2019.

Policy network improves learning from positive and unlabeled data (common in e-commerce).

[bibtex]
@InProceedings{LiICDM2019,
author =   {Li, T. and Wang, C.-C. and Ma, Y. and Ortal, P. and Zhao, Q. 
            and Stenger, B. and Hirate, Y.},
title =    {Learning Classifiers on Positive and Unlabeled Data with 
            Policy Gradient},
booktitle = {IEEE International Conference on Data Mining (ICDM)},
year =      {2019},
month =     {November}
}
A Photo Booth That Finds Your Sports Player Lookalike
M. Nakazawa, T. Mukasa, B. Stenger
Machine Vision Applications (MVA), May 2019.

Face similarity search for digital signage enjoyed by over 12K baseball fans.

[bibtex]
@InProceedings{NakazawaMVA2019,
  author =   {Nakazawa, M. and Mukasa, T. and Stenger, B.},
  title =    {A Photo Booth That Finds Your Sports Player Lookalike},
  booktitle = {MVA},
  year =      {2019},
  month =     {May},
  pdf   =     {nakazawa_mva2019.pdf}
}
Trajectories as Topics: Multi-Object Tracking by Topic Discovery
W. Luo, B. Stenger, X. Zhao, T.-K.Kim
IEEE Trans. Image Processing, Vol. 29(1), January 2019.

Multi-target object tracking with a topic discovery approach.

[bibtex]
@InJournal{LuoTIP2019},
  title = {Trajectories as Topics: Multi-Object Tracking by Topic Discovery},
  author = {Luo, W. and Stenger, B. and Zhao, X. and Kim, T.-K.},
  booktitle = {IEEE Trans. Image Processing},
  year = {2019},
  volume = {29},
  number = {1},
  month = {January},
  pdf = {luo_tip2018.pdf}
  }
    
Deep Heterogeneous Autoencoders for Collaborative Filtering
T. Li, Y. Ma, J. Xu, B. Stenger, C. Liu, Y. Hirate.
IEEE International Conference on Data Mining (ICDM), November 2018.

Autoencoder-based recommender system that takes into account multiple data sources, including the purchase history.

[bibtex]
@InProceedings{LiICDM2018,
  author = {Li, T. and Ma, Y. and Xu, J. and Stenger, B. and Liu, C. 
            and Hirate, Y.},
  title  = {Deep Heterogeneous Autoencoders for Collaborative Filtering},
  booktitle = {IEEE International Conference on Data Mining (ICDM)},
  year   = {2018},
  month = {November},
  pdf = {li_icdm2018.pdf}
}
    
Dense ByNet: Residual Dense Network for Image Super Resolution
J. Xu, Y. Chae, B. Stenger, A. Datta
ICIP, October 2018.

CNN-based image super-resolution with high speed & low distortion, improved over ICIP 2017 paper.

[bibtex]
@InProceedings{XuICIP2018,
  author = {Xu, J. and Chae, Y. and Stenger, B. and Datta, A.},
  title  = {Dense ByNet: Residual Dense Network for Image Super Resolution},
  booktitle = {Int. Conf. Image Processing (ICIP)},
  year =      {2018},
  month =     {October},
  pdf = {xu_icip2018.pdf}
}
    
3D Hand Pose Estimation: From Current Achievements to Future Goals
S. Yuan, G. Garcia-Hernando, B. Stenger, G. Moon, J. Y. Chang, K. M. Lee, P. Molchanov, J. Kautz, S. Honari, L. Ge, J. Yuan, X. Chen, G. Wang, F. Yang, K. Akiyama, Y. Wu, Q. Wan, M. Madadi, S. Escalera, S. Li, D. Lee, I. Oikonomidis, A. Argyros, and T.-K. Kim,
CVPR, June 2018.

Analysis of the top performing methods in the Hands in the Million Challenge.

[arxiv] [bibtex]
@InProceedings{YuanCVPR2018,
  author =   {Yuan, S. and Garcia-Hernando, G. and Stenger, B. and  Moon, G. 
              and  Chang, J. Y. and Lee, K. M. and  Molchanov, P. and 
              Kautz, J. and Honari, S. and  Ge, L. and  Yuan, J. and  
              Chen, X. and Wang, G. and Yang, F. and Akiyama, K. and Wu, Y. 
              and Wan, Q. and Madadi, M. and Escalera, S. and Li, S. and 
              Lee, D. and Oikonomidis, I. and Argyros, A. and Kim, T.-K.},
  title =    {3D Hand Pose Estimation: From Current Achievements 
              to Future Goals},
  booktitle = {CVPR},
  year =      {2018},
  month =     {June}
}
    
ByNet-SR: Image Super Resolution with a Bypass Connection Network
J. Xu, Y. Chae, B. Stenger,
ICIP, September 2017.

CNN-based image super-resolution with high speed & quality.

[bibtex][code]
@InProceedings{XuICIP2017,
  author = {Xu, J. and Chae, Y. and Stenger, B.},
  title  = {{ByNet-SR}: Image Super Resolution with a 
            Bypass Connection Network},
  year   = {2017},
  month = {September},
  booktitle = {ICIP}
}
    
BigHand2.2M Benchmark: Hand Pose Data Set and State of the Art Analysis
S. Yuan, Q. Ye, B. Stenger, S. Jain, T.-K. Kim,
CVPR, July 2017.

We captured a new standard dataset for 3D hand pose estimation. Depth maps are accurately annotated with 3D joint locations using a magnetic tracking system. We show that training a CNN on this data achieves accurate results. The data was used in the Hands in the Million Challenge.

[arxiv] [bibtex]

@InProceedings{YuanCVPR2017,
  author =   {Yuan, S. and Ye, Q. and Stenger, B. 
              and Jain, S. and Kim, T.-K."},
  title =    {BigHand2.2M Benchmark: Hand Pose Data Set 
              and State of the Art Analysis},
  booktitle = {CVPR},
  year =      {2017},
  month =     {July}
}
    
Parsing Floor Plan Images
S. Dodge, J. Xu, B. Stenger,
MVA, May 2017.

Wall segmentation using fully convolutional networks (FCN) and applications in furniture fitting and 3D modeling

[R-FP dataset] [video] [bibtex]
@InProceedings{DodgeMVA2017,
   author  = {Dodge, S. and Xu, J. and Stenger, B.},
   title   = {Parsing Floor Plan Images},
   year    = {2017},
   month   = {May},
   booktitle = {MVA}
}
    
Pano2CAD: Room Layout From A Single Panorama Image
J. Xu, B. Stenger, T. Kerola, T. Tung,
WACV, March 2017.

Estimating 3D room geometry from a single panorama image using surface normal estimation, 2D object detection and 3D object pose estimation

[arxiv] [bibtex]
@InProceedings{XuWACV2017,
   author  = {Xu, J. and Stenger, B. and Kerola T. and Tung, T.},
   title   = {Pano2CAD: Room Layout From A Single Panorama Image},
   year    = {2017},
   month   = {March},
   booktitle = {WACV}
}
    
design credits