Rémi Emonet's Research Home     (see global home)

Selection of Recent Publications     (see all publications and details)

  • Year 2019
    W
    Interpreting Neural Networks as Majority Votes through the PAC-Bayesian Theory
    Paul Viallard, Rémi Emonet, Pascal Germain, Amaury Habrard, Emilie Morvant
    2019
    - NeurIPS 2019 Workshop on Machine Learning with Guarantees
    [bibtex] (click to show) 
    @inproceedings{viallard2019interpreting,
  title={Interpreting Neural Networks as Majority Votes through the PAC-Bayesian Theory},
  author={Viallard, Paul and Emonet, R{\'e}mi and Germain, Pascal and Habrard, Amaury and Morvant, Emilie},
  booktitle = {NeurIPS 2019 Workshop on Machine Learning with Guarantees},
  year={2019}
}
    C
    An Adjusted Nearest Neighbor Algorithm Maximizing the F-measure from Imbalanced Data
    Rémi Viola, Rémi Emonet, Amaury Habrard, Guillaume Metzler, Stéphane Riou, Marc Sebban
    2019
    - ICTAI (International Conference on Tools with Artificial Intelligence)
    [bibtex] (click to show) 
    @inproceedings{metzler2019gnn,
  title={An Adjusted Nearest Neighbor Algorithm Maximizing the F-measure from Imbalanced Data},
  author={ and Emonet, R{\'e}mi and Fromont, Elisa},
  booktitle={IEEE International Conference on Image Processing},
  year={2019}
}
    C
    From Cost-Sensitive Classification to Tight F-measure Bounds
    Kevin Bascol, Rémi Emonet, Élisa Fromont, Amaury Habrard, Guillaume Metzler, Marc Sebban
    2019
    - AISTATS
    [bibtex] (click to show) 
    @inproceedings{bascolmetzlerfmeasure,
  title={From Cost-Sensitive Classification to Tight F-measure Bounds},
  author={Bascol, Kevin and Emonet, Rémi and Fromont, Élisa and Habrard, Amaury and Metzler, Guillaume and Sebban, Marc},
  booktitle={AISTATS 2019},
  year={2019}
}
  • Year 2018
    C
    Fast and Provably Effective Multi-view Classification with Landmark-based SVM
    Valentina Zantedeschi, Rémi Emonet, Marc Sebban
    2018
    - ECML-PKDD
    https://github.com/vzantedeschi/multiviewLSVM
    [bibtex] (click to show) 
    @inproceedings{zantedeschi2018metric,
  title={ Fast and Provably Effective Multi-view Classification with Landmark-based SVM },
  author={Zantedeschi, Valentina and Emonet, R{\'e}mi and Sebban, Marc},
  booktitle={ECML-PKDD 2018},
  year={2018}
}
  • Year 2017
    B
    Unsupervised Domain Adaptation Based on Subspace Alignment
    Basura Fernando, Rahaf Aljundi, Rémi Emonet, Amaury Habrard, Marc Sebban, Tinne Tuytelaars
    2017
    - Domain Adaptation in Computer Vision Applications
    [bibtex] (click to show) 
    @incollection{fernando2017unsupervised,
  title={Unsupervised Domain Adaptation Based on Subspace Alignment},
  author={Fernando, Basura and Aljundi, Rahaf and Emonet, R{\'e}mi and Habrard, Amaury and Sebban, Marc and Tuytelaars, Tinne},
  booktitle={Domain Adaptation in Computer Vision Applications},
  pages={81--94},
  year={2017},
  publisher={Springer}
}
@book{csurka2017domain,
  title={Domain Adaptation in Computer Vision Applications},
  author={Csurka, Gabriela},
  year={2017},
  publisher={Springer},
  ISBN={978-3-319-58346-4},
  DOI={10.1007/978-3-319-58347-1},
  URL={http://www.springer.com/gp/book/9783319583464}
}
    C
    Residual Conv-Deconv Grid Network for Semantic Segmentation
    Damien Fourure, Rémi Emonet, Élisa Fromont, Damien Muselet, Alain Trémeau, Christian Wolf
    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
    Damien Fourure, Rémi Emonet, Élisa Fromont, Damien Muselet, Natalia Neverova, Alain Trémeau, Christian Wolf
    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
    Valentina Zantedeschi, Rémi Emonet, Marc Sebban
    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}
}
  • Year 2015
    C
    Landmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation
    Rahaf Aljundi, Rémi Emonet, Damien Muselet, Marc Sebban
    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
    Rémi Emonet, Jagannadan Varadarajan, Jean-Marc Odobez
    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
    Jagannadan Varadarajan, Rémi Emonet, Jean-Marc Odobez
    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
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -
    -

Demos

For now, visit my videos page.

Presentations (research and related)

Here are presentations that I made publicly enough so that it makes sense to share them. (click the icon on the left to see the sources and a PDF export)

gh[2020-01-23]  Défi IA − Anomaly Detection: class imbalance or novelty
gh[2019-06-13]  Invitied Talk at NAVER LABS − Dealing with Imbalanced Data, and, Interpretability via Adversarial Regularization
gh[2018-06-07]  A Tour of Machine Learning and its Subdomains
gh[2018-06-06]  Domain Adaptation and Multi-view Learning: using subspace alignment and landmark projections
gh[2017-04-22]  Deep Learning pour la Reconnaissance de Chatons
gh[2017-01-20]  Version control with Git at CIRAD − 2017
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.