{"id":57,"date":"2015-04-16T09:28:36","date_gmt":"2015-04-16T07:28:36","guid":{"rendered":"https:\/\/project.inria.fr\/semapolis\/?page_id=57"},"modified":"2021-09-06T19:32:46","modified_gmt":"2021-09-06T17:32:46","slug":"publications","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/semapolis\/fr\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"

D\u00e9sol\u00e9, cet article est seulement disponible en English<\/a>.<\/p>

<\/p>\n

International Journals<\/h4>\n
    \n
  1. <\/a>[Arandjelovic et al. PAMI 2017]<\/strong>
    \n    NetVLAD: CNN architecture for weakly supervised place recognition<\/a>.<\/strong> Relja Arandjelovic, Petr Gronat, Akihiko Torii, Tomas Pajdla, Josef Sivic. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI 2017<\/strong>). See also the\u00a0project page<\/a><\/span>.<\/li>\n
  2. <\/a>[Aubry et al. TOG 2104]<\/strong>
    \n    Painting-to-3D Model Alignment Via Discriminative Visual Elements<\/a>.<\/strong>\u00a0Mathieu Aubry, Bryan Russell, Josef Sivic. ACM Transactions on Graphics (TOG 2014<\/strong>), 33(2), 2014. Also in International Conference on Computer Graphics and Interactive Techniques (SIGGRAPH 2014<\/strong>). See also the\u00a0project page<\/a><\/span>. (a)<\/strong><\/li>\n
  3. <\/a>[Boulch et al. CGF 2014]<\/strong>
    \n    Piecewise-Planar 3D Reconstruction with Edge and Corner Regularization<\/a>.<\/strong>\u00a0Alexandre Boulch and Martin de La Gorce, Renaud Marlet. Computer Graphics Forum (CGF 2014<\/strong>), 33(5):55-64. Also in 12th Eurographics Symposium on Geometry (SGP 2014<\/strong>). (b)<\/strong><\/li>\n
  4. <\/a>[Dalens et al. PAMI 2019]<\/strong>
    \n    Bilinear image translation for temporal analysis of photo collections<\/a>.<\/strong> Th\u00e9ophile Dalens, Mathieu Aubry, Josef Sivic. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI 2019<\/strong>). See also the\u00a0project page<\/a><\/span>.<\/li>\n
  5. <\/a>[Gadde et al. IJCV 2016]<\/strong>
    \n    Learning grammars for architecture-specific facade parsing<\/a>.<\/strong> Raghudeep Gadde, Renaud Marlet, Nikos Paragios. International Journal of Computer Vision (IJCV 2016<\/strong>), 117(3):290-316, March 2016. See also the\u00a0used dataset<\/a><\/span>.<\/li>\n
  6. <\/a>[Gadde et al. PAMI 2018]<\/strong>
    \n    Efficient 2D and 3D Facade Segmentation using Auto-Context<\/a>.<\/strong> Raghudeep Gadde, Varun Jampani, Renaud Marlet, Peter Gehler. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI 2018<\/strong>). See also the\u00a0project page<\/a><\/span>\u00a0and the supplementary material<\/a><\/span>.<\/li>\n
  7. <\/a>[Hedman et al. TOG 2016]<\/strong>
    \n    Scalable Inside-Out Image-Based Rendering<\/a>.<\/strong> Peter Hedman, Tobias Ritschel, George Drettakis, Gabriel Brostow. ACM Transactions on Graphics (TOG 2016<\/strong>), 35(6). Also in SIGGRAPH Asia Conference (SIGGRAPH Asia 2016<\/strong>).\u00a0See also the\u00a0short project page<\/a><\/span> and complete project page<\/a><\/span>.<\/li>\n
  8. <\/a>[Landrieu & Obozinski SIIMS 2017]<\/strong>
    \n    Cut Pursuit: fast algorithms to learn piecewise constant functions on general weighted graphs<\/a>.<\/strong> Lo\u00efc Landrieu, Guillaume Obozinski. SIAM Journal on Imaging Sciences (SIIMS 2017<\/strong>), 10(4), 1724\u20131766, 2017. See also the\u00a0project page<\/a><\/span>.<\/li>\n
  9. <\/a>[Nishida et al. TOG 2016]<\/strong>
    \n    Interactive Sketching of Urban Procedural Models<\/a><\/strong>. Gen Nishida, Ignacio Garcia-Dorado, Daniel G. Aliaga, Bedrich Benes, Adrien Bousseau. ACM Transactions on Graphics (TOG 2016<\/strong>). Also in SIGGRAPH Conference (SIGGRAPH 2016<\/strong>). See also the\u00a0short project page<\/a><\/span> and complete project page<\/a><\/span>.<\/li>\n
  10. <\/a>[Thonat et al. CGF 2018]<\/strong>
    \n    Thin Structures in Image Based Rendering<\/a>.<\/strong>\u00a0Theo Thonat, Abdelaziz Djelouah, Fr\u00e9do Durand, George Drettakis.\u00a0Computer Graphics Forum (CGF 2018<\/strong>), 37(4), 2018. Also in Eurographics Symposium on Rendering (EGSR 2018<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
  11. <\/a>[Torii et al. PAMI 2015]<\/strong>
    \n    Visual place recognition with repetitive structures<\/strong><\/a>.<\/strong> Akihiko Torii, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI 2015<\/strong>), 37(11):2346-2359, November 2015. See also the\u00a0project page<\/a><\/span>. (a)<\/strong><\/li>\n
  12. <\/a>[Torii et al. PAMI 2017]<\/strong>
    \n    24\/7 place recognition by view synthesis<\/strong><\/a>.<\/strong> Akihiko Torii, Relja Arandjelovic, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI 2017<\/strong>). See also the project page<\/a><\/span>.<\/li>\n<\/ol>\n

    Book Chapters<\/h4>\n
      \n
    1. <\/a>[Aubry et al. chapter LSVG 2015]<\/strong>
      \n      Visual geo-localization of non-photographic depictions via 2D-3D alignment<\/a>.<\/strong>\u00a0Mathieu Aubry, Bryan Russell, Josef Sivic. Chapter in book\u00a0Large-Scale Visual Geolocalization<\/em> (chapter LSVG 2015)<\/strong>, Amir Roshan Zamir, Asaad Hakeem, Mubarak Shah, Luc Van Gool, Richard Szeliski (Eds), Springer.<\/li>\n<\/ol>\n

      International Conferences<\/h4>\n
        \n
      1. <\/a>[Arandjelovic et al. CVPR 2016]<\/strong>
        \n        NetVLAD: CNN architecture for weakly supervised place recognition<\/a>.<\/strong> Relja Arandjelovic, Petr Gronat, Akihiko Torii, Tomas Pajdla, Josef Sivic. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016<\/strong>).\u00a0See also the\u00a0project page<\/a><\/span>.<\/li>\n
      2. <\/a>[Aubry et al. CVPR 2014]<\/strong>
        \n        Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models<\/a>.<\/strong>\u00a0Mathieu Aubry, Daniel Maturana, Alexei A. Efros, Bryan Russell, Josef Sivic. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014<\/strong>). \u00a0See also the project page<\/a><\/span>.\u00a0(a)<\/strong><\/li>\n
      3. <\/a>[Aubry & Russell ICCV 2015]<\/strong>
        \n        Understanding deep features with computer-generated imagery<\/a>.<\/strong> Mathieu Aubry, Bryan Russell. IEEE International Conference on Computer Vision (ICCV 2015<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      4. <\/a>[Boulch & Marlet ICPR 2014]<\/strong>
        \n        Statistical criteria for shape fusion and selection<\/a>.<\/strong>\u00a0Alexandre Boulch, Renaud Marlet. 22nd International Conference on Pattern Recognition (ICPR 2014<\/strong>). See also the code repository<\/a><\/span>. (b)<\/strong><\/li>\n
      5. <\/a>[Bourki et al. WACV 2017]<\/strong>
        \n        Patchwork Stereo: Scalable, Structure-aware 3D Reconstruction in Man-made Environments<\/a>.<\/strong> Amine Bourki, Martin de La Gorce, Renaud Marlet, Nikos Komodakis. IEEE Winter Conference on Applications of Computer Vision (WACV 2017<\/strong>).\u00a0See also the supplementary material<\/a><\/span>.<\/li>\n
      6. <\/a>[Djelouah et al. 3DV 2016]<\/strong>
        \n        Cotemporal Multi-View Video Segmentation<\/a>.<\/strong> Abdelaziz Djelouah, Jean-S\u00e9bastien Franco, Edmond Boyer, Patrick P\u00e9rez, George Drettakis. International Conference on 3D Vision (3DV 2016<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      7. <\/a>[Gidaris & Komodakis ICCV 2015]<\/strong>
        \n        Object Detection via a Multi-region and Semantic Segmentation-aware CNN Model<\/a>.<\/strong> Spyros Gidaris, Nikos Komodakis. IEEE International Conference on Computer Vision (ICCV 2015<\/strong>). See also the extended technical report<\/a><\/span> and code repository<\/a><\/span>.<\/li>\n
      8. <\/a>[Gidaris & Komodakis CVPR 2016]<\/strong>
        \n        LocNet: Improving Localization Accuracy for Object Detection<\/a>.<\/strong> Spyros Gidaris, Nikos Komodakis. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016<\/strong>).\u00a0See also the extended technical report<\/a><\/span> and code repository<\/a><\/span>.<\/li>\n
      9. <\/a>[Gidaris & Komodakis BMVC 2016]<\/strong>
        \n        Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization<\/a>.<\/strong> Spyros Gidaris, Nikos Komodakis. 27th British Machine Vision Conference (BMVC 2016<\/strong>). See also the code repository<\/a><\/span>.<\/li>\n
      10. <\/a>[Gidaris & Komodakis CVPR 2017]<\/strong>
        \n        Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling<\/a>.<\/strong> Spyros Gidaris, Nikos Komodakis. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017<\/strong>). See also the extended technical report<\/a><\/span>\u00a0with preliminary results in semantic segmentation tasks as well as the\u00a0result repository<\/a><\/span>.<\/li>\n
      11. <\/a>[Gidaris & Komodakis CVPR 2018]<\/strong>
        \n        Dynamic Few-Shot Visual Learning without Forgetting<\/a>.<\/strong>\u00a0Spyros Gidaris, Nikos Komodakis. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      12. <\/a>[Gidaris et al. ICLR 2018]<\/strong>
        \n        Unsupervised Representation Learning by Predicting Image Rotations<\/a>.<\/strong>\u00a0Spyros Gidaris, Praveer Singh, Nikos Komodakis. International Conference on Learning Representations (ICLR 2018<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      13. <\/a>[Jampani et al. WACV 2015]<\/strong>
        \n        Efficient Facade Segmentation using Auto-Context<\/a>.<\/strong>\u00a0Varun Jampani, Raghudeep Gadde, Peter V. Gehler. IEEE Winter Conference on Applications of Computer Vision (WACV 2015<\/strong>).\u00a0See also the\u00a0project page<\/span><\/a>.<\/li>\n
      14. <\/a>[Kozi\u0144ski & Marlet WACV 2014]<\/strong>
        \n        Image Parsing with Graph Grammars and Markov Random Fields<\/a>.<\/strong>\u00a0Mateusz Kozi\u0144ski, Renaud Marlet. IEEE Winter Conference on Applications of Computer Vision (WACV 2014<\/strong>). (a)<\/strong><\/li>\n
      15. <\/a>[Kozi\u0144ski et al. ACCV 2014]<\/strong>
        \n        Beyond procedural facade parsing: Bidirectional alignment via linear programming<\/a>.<\/strong> Mateusz Kozi\u0144ski, Guillaume Obozinski, Renaud Marlet. In 12th Asian Conference on Computer Vision (ACCV 2014<\/strong>). See also the supplementary material<\/a><\/span>.<\/li>\n
      16. <\/a>[Kozi\u0144ski et al. CVPR 2015]<\/strong>
        \n        A MRF Shape Prior for Facade Parsing with Occlusions<\/a>.<\/strong> Mateusz Kozi\u0144ski, Raghudeep Gadde, Sergey Zagoruyko, Renaud Marlet, Guillaume Obozinski. In 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015<\/strong>).\u00a0See also the supplementary material<\/a><\/span>.<\/li>\n
      17. <\/a>[Kozi\u0144ski et al. NeurIPSw 2017]<\/strong>
        \n        An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks<\/a>.<\/strong> Mateusz Kozi\u0144ski, Lo\u00efc Simon, Fr\u00e9d\u00e9ric Jurie. Limited Labeled Data workshop at Neural Information Processing Systems (NeurIPSw 2017<\/strong>).<\/li>\n
      18. <\/a>[Lee et al. ICCP 2015]<\/strong>
        \n        Linking Past to Present: Discovering Style in Two Centuries of Architecture<\/a>.<\/strong> Stefan Lee, Nicolas Maisonneuve, Alexei Efros, Josef Sivic, David Crandall, International Conference on Computational Photography (ICCP 2015<\/strong>). See also the supplementary material<\/a><\/span>, the\u00a0project page<\/a><\/span>. and the interactive online demo<\/a>.<\/li>\n
      19. <\/a>[Massa et al. CVPR 2016]<\/strong>
        \n        Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views<\/a>.<\/strong> Francisco Massa, Bryan Russell, Mathieu Aubry. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      20. <\/a>[Massa et al. BMVC 2016]<\/strong>
        \n        Crafting a multi-task CNN for viewpoint estimation<\/a>.<\/strong> Francisco Massa, Renaud Marlet, Mathieu Aubry. 27th British Machine Vision Conference (BMVC 2016<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      21. <\/a>[Oquab et al. CVPR 2015]<\/strong>
        \n        Is object localization for free? – Weakly-supervised learning with convolutional neural networks<\/a>.<\/strong> Maxime Oquab, L\u00e9on Bottou, Ivan Laptev, Josef Sivic.\u00a0IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015<\/strong>).<\/li>\n
      22. <\/a>[Ortiz-Cayon et al. 3DV 2015]<\/strong>
        \n        A Bayesian Approach for Selective Image-Based Rendering using Superpixels<\/a>.<\/strong> Rodrigo Ortiz-Cayon, Abdelaziz Djelouah, George Drettakis. International Conference on 3D Vision (3DV 2015<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      23. <\/a>[Ortiz-Cayon et al. 3DV 2016]<\/strong>
        \n        Automatic 3D Car Model Alignment for Mixed Image-Based Rendering<\/a>.<\/strong> Rodrigo Ortiz-Cayon, Abdelaziz Djelouah, Francisco Massa, Mathieu Aubry, George Drettakis. International Conference on 3D Vision (3DV 2016<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      24. <\/a>[Philip & Drettakis I3D 2018]<\/strong>
        \n        Plane-Based Multi-View Inpainting for Image-Based Rendering in Large Scenes<\/a>.<\/strong>\u00a0Julien Philip, George Drettakis.\u00a0ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D 2018<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      25. <\/a>[Rocco et al. CVPR 2017]<\/strong>
        \n        Convolutional Neural Network Architecture for Geometric Matching<\/a>.<\/strong> Ignacio Rocco, Relja Arandjelovic, Josef Sivic. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      26. <\/a>[Thonat et al. 3DV 2016]<\/strong>
        \n        Multi-View Inpainting for Image-Based Scene Editing and Rendering<\/a>.<\/strong> Theo Thonat, Eli Shechtman, Sylvain Paris, George Drettakis. International Conference on 3D Vision (3DV 2016<\/strong>). See also the project page<\/a><\/span>.<\/li>\n
      27. <\/a>[Torii et al. CVPR 2015]<\/strong>
        \n        24\/7 place recognition by view synthesis<\/a>.<\/strong> Akihiko Torii, Relja Arandjelovic, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015<\/strong>). See also the project page<\/a><\/span>.<\/li>\n<\/ol>\n

        Technical report<\/h4>\n
          \n
        1. <\/a>[Keriven Acute3D report 2019]<\/strong>
          \nAm\u00e9lioration de la reconstruction 3D.<\/strong> Renaud Keriven. Acute3D \/ Bentley Systems technical report, 2019. In French. Confidential.<\/li>\n<\/ol>\n

          Awards<\/h4>\n

          Spyros Gidaris, PhD student funded by Semapolis, received two awards for his thesis entitled \u00ab\u00a0Effective and annotation-efficient deep learning for image understanding\u00a0\u00bb:<\/p>\n

            \n
          1. the best PhD thesis award (2019)<\/a>\u00a0from Ecole des Ponts ParisTech<\/a>,<\/li>\n
          2. the best PhD thesis award (2019)<\/a>\u00a0from University of Paris-Est<\/a> (Mathematics and ICT doctoral school<\/a>).<\/li>\n<\/ol>\n

            Legend<\/h3>\n