Rémi Emonet's Research Home     (see global home)

Selection of Recent Publications     (see all publications and details)

  • Year 2017
    C
    Residual Conv-Deconv Grid Network for Semantic Segmentation
    2017
    - BMVC (British Machine Vision Conference)
    https://github.com/Fourure/GridNet
    [bibtex] (click to show)
    @inproceedings{fourure2017gridnet,
      title={Residual Conv-Deconv Grid Network for Semantic Segmentation},
      author={Fourure, Damien and Emonet, R{\'e}mi and Fromont, Elisa and Muselet, Damien and Tr{\'e}meau, Alain and Wolf, Christian},
      booktitle={Proceedings of the British Machine Vision Conference, 2017},
      year={2017}
    }
    
    J
    Multi-task, Multi-domain Learning: application to semantic segmentation and pose regression
    2017
    - Neurocomputing
    [bibtex] (click to show)
    @article{fourure2017multi,
      title={Multi-task, Multi-domain Learning: application to semantic segmentation and pose regression},
      author={Fourure, Damien and Emonet, R{\'e}mi and Fromont, Elisa and Muselet, Damien and Neverova, Natalia and Tr{\'e}meau, Alain and Wolf, Christian},
      journal={Neurocomputing},
      volume={251},
      pages={68--80},
      year={2017},
      publisher={Elsevier}
    }
    
  • Year 2016
    C
    beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data
    2016
    - NIPS (Neural Information Processing Systems)
    http://vzantedeschi.com/betarisk.html
    [bibtex] (click to show)
    @inproceedings{zantedeschi2016beta,
      title={beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data},
      author={Zantedeschi, Valentina and Emonet, R{\'e}mi and Sebban, Marc},
      booktitle={NIPS 2016},
      year={2016}
    }
    
    C
    Semantic Segmentation via Multi-task, Multi-domain Learning
    2016
    - SSPR (Structural and Syntactic Pattern Recognition)
    [bibtex] (click to show)
    C
    Metric Learning as Convex Combinations of Local Models with Generalization Guarantees
    2016
    - CVPR (IEEE conf. Computer Vision and Pattern Recognition)
    [bibtex] (click to show)
    @inproceedings{zantedeschi2016metric,
      title={Metric learning as convex combinations of local models with generalization guarantees},
      author={Zantedeschi, Valentina and Emonet, R{\'e}mi and Sebban, Marc},
      booktitle={CVPR2016},
      year={2016}
    }
    
  • Year 2015
    C
    Landmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation
    2015
    - CVPR (IEEE conf. Computer Vision and Pattern Recognition)
    [bibtex] (click to show)
    @inproceedings{aljundi2015landmarks,
      title={Landmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation},
      author={Aljundi, Rahaf and Emonet, R{\'e}mi and Muselet, Damien and Sebban, Marc},
      booktitle={Computer Vision and Pattern Recognition},
      year={2015}
    }
    
  • Year 2014
    J
    Temporal Analysis of Motif Mixtures using Dirichlet Processes
    2014
    - TPAMI (Transactions on Pattern Analysis and Machine Intelligence)
    [bibtex] (click to show)
    @ARTICLE{Emonet_PAMI_2014,
             author = {Emonet, Remi and Varadarajan, Jagannadan and Odobez, Jean-Marc},
              title = {Temporal Analysis of Motif Mixtures using Dirichlet Processes},
            journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
               year = {2014}
    }
    
    B
    Sparsity in Topic Models
    2014
    - Practical Applications of Sparse Modeling: Biology, Signal Processing and Beyond
    [bibtex] (click to show)
    @INCOLLECTION {Varadarajan_MITPRESS_2012,
        title = {Sparsity in Topic Models},
       author = {Varadarajan, Jagannadan and Emonet, Remi and Odobez, Jean-Marc},
    booktitle = {Practical Applications of Sparse Modeling (Neural Information Processing series)},
         year = {2014},
    publisher = {MIT Press},
          pdf = {https://publidiap.idiap.ch/downloads//papers/2012/Varadarajan_MITPRESS_2012.pdf},
    }
    @book{9780262027724,
      Author = {},
      Title = {Practical Applications of Sparse Modeling (Neural Information Processing series)},
      Publisher = {The MIT Press},
      Year = {2014},
      ISBN = {0262027720},
      URL = {http://www.amazon.com/Practical-Applications-Modeling-Information-Processing/dp/0262027720%3FSubscriptionId%3D0JYN1NVW651KCA56C102%26tag%3Dtechkie-20%26linkCode%3Dxm2%26camp%3D2025%26creative%3D165953%26creativeASIN%3D0262027720}
    }
    
  • Year
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -

Presentations (research and related)

Here are presentations that I made publicly enough so that it makes sense to share them.

gh[2017-04-22]  Deep Learning pour la Reconnaissance de Chatons
gh[2017-01-20]  Version control with Git at CIRAD
gh[2017-01-04]  Likelihood-based and Likelihood-free Unsupervised Learning
gh[2016-12-13]  A Tour of Probabilistic and Deep Approaches for Unsupervised Learning − Optim. and ML Day
gh[2016-09-01]  Introduction to Version Control using Git and Gitlab − 2016
gh[2016-05-25]  Learn to Learn: Facts About Learning − Web En Vert
gh[2016-02-11]  About Sparsity and Sparsity in Probabilistic Modeling
gh[2015-11-27]  Unsupervised Domain Adaptation, Deep CNNs − Xerox Research Center Europe
gh[2015-11-26]  Deep Learning Frameworks − Saintélyon Deep Learning Workshop
gh[2015-09-30]  Machine Learning Introduction − Web En Vert
gh[2015-04-30]  Dirichlet Processes for GMM − Image&Tracking group
gh[2014-06-20]  Fisher Kernel and Fisher Vectors − ANR SoLSTiCe project
gh[2014-05-15]  Probabilistic Views of Classical Problems − About probabilities and prior
[2014-03-10] Temporal Topic Models for Probabilistic Motif Mining − SMiLe2014
gh[2014-10-23]  Introduction to Version Control using Git and Gitlab − 2014
gh[2013-10-03]  Introduction to Version Control using Git and Gitlab − 2013

Research Software and Related Projects

Temporal probabilistic models website. Implementation of EM-style and non-parametric models (Gibbs sampling). Sharing code from our work done mostly while at the Idiap research institute.
Human detection source code, used in the VANAHEIM project. I mostly worked on the finalization, cleanup and packaging, and on the website.
The framework I use and improve to build my teaching and research slides.
A modular framework to make executables by assembling modules in Java, C++ and Python. Created and used during my stay in INRIA-PRIMA and at Idiap (in the VANAHEIM project).
A Gaussian pyramid processor using kernels in OpenCL with C and Java interfaces. It implements the square-rooted version which does less processing.
A service oriented middleware for ambient intelligence and pervasive computing. Works across operating systems and programming languages. Developed in INRIA-PRIMA at the time of my Ph.D. Thesis.