{"id":74,"date":"2017-01-09T10:05:43","date_gmt":"2017-01-09T09:05:43","guid":{"rendered":"https:\/\/project.inria.fr\/decore\/?page_id=74"},"modified":"2020-01-07T08:48:55","modified_gmt":"2020-01-07T07:48:55","slug":"publications","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/decore\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"<p>2019<\/p>\n<ul>\n<li><a href=\"https:\/\/hal.archives-ouvertes.fr\/hal-01886285\/file\/main.pdf\" target=\"_blank\" rel=\"noopener\">Adaptive Density Estimation for Generative Models<\/a>. Thomas Lucas, Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari, Jakob Verbeek.\u00a0<i>NeurIPS 2019 &#8211; Thirty-third Conference on Neural Information Processing Systems<\/i>, Dec 2019, Vancouver, Canada.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-02268466\/file\/PRN_BMVC19.pdf\">Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image.\u00a0<\/a>Roman Klokov, Jakob Verbeek, Edmond Boyer.\u00a0<em>BMVC 2019 &#8211; British Machine Vision Conference<\/em>, Sep 2019, Cardiff, United Kingdom.<\/li>\n<li><a href=\"https:\/\/hal.archives-ouvertes.fr\/hal-02267564\/file\/CNMM_ICCV2019.pdf\">Adaptative Inference Cost With Convolutional Neural Mixture Models.<\/a> Adri\u00e0 Ruiz, Jakob Verbeek.<br \/>\n<em>ICCV 2019 &#8211; International Conference on Computer Vision<\/em>, Oct 2019, Seoul, South Korea.<\/li>\n<li><a href=\"https:\/\/hal.archives-ouvertes.fr\/hal-02177151\/file\/paper_arXiv_ICML2019-3.pdf\">Understanding Priors in Bayesian Neural Networks at the Unit Level.<\/a> Mariia Vladimirova, Jakob Verbeek, Pablo Mesejo, Julyan Arbel.\u00a0 <em>ICML 2019 &#8211; 36th International Conference on Machine Learning<\/em>, Jun 2019, Long Beach, United States.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01896007\/file\/RbVAES_HAL.pdf\">Learning Disentangled Representations with Reference-Based Variational Autoencoders.<\/a><br \/>\nAdri\u00e0 Ruiz, Oriol Martinez, Xavier Binefa, Jakob Verbeek. <em>ICLR workshop on Learning from Limited Labeled Data<\/em>, May 2019, New Orleans, United States.<\/li>\n<\/ul>\n<p>2018<\/p>\n<ul>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01900418\/file\/manuscript.pdf\">Sparse weakly supervised models for object localization in road environment.<\/a> Valentina Zadrija, Josip Krapac, Sini\u0161a \u0160egvi\u0107, Jakob Verbeek. <em>Computer Vision and Image Understanding<\/em>, to appear.<\/li>\n<li><a href=\"https:\/\/hal.archives-ouvertes.fr\/hal-01886285\/file\/main.pdf\">Coverage and quality driven training of generative image models.<\/a> Konstantin Shmelkov, Thomas Lucas, Karteek Alahari, Cordelia Schmid, Jakob Verbeek. <em>Preprint.<\/em><\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01867143\/file\/li18eccvw.pdf\">Scene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization.<\/a><br \/>\nXiaotian Li, Xiaotian Li, Juha Ylioinas, Jakob Verbeek, Juho Kannala. <em>ECCV 2018 &#8211; Workshop Geometry Meets Deep Learning<\/em>, Sep 2018, Munich, Germany<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01867746\/file\/couprie18eccvw.pdf\">Joint Future Semantic and Instance Segmentation Prediction.<\/a> Camille Couprie, Pauline Luc, Jakob Verbeek.\u00a0<i>ECCV Workshop on Anticipating Human Behavior<\/i>, 2018, Munich, Germany.<\/li>\n<li><a href=\"https:\/\/openreview.net\/forum?id=rylRCUJDG\">Coupled Ensembles of Neural Networks<\/a>, Anuvabh Dutt, Denis Pellerin, Georges Qu\u00e9not. <em>International Conference on Learning Representations (ICLR) &#8211; Workshop Track, <\/em>May 2018, Vancouver, Canada.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01851612\/document\" target=\"_blank\" rel=\"noopener\"> Pervasive Attention &#8211; 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction.<\/a> Maha Elbayad, Laurent Besacier, Jakob Verbeek.\u00a0<i>CoNLL 2018 &#8211; The SIGNLL Conference on Computational Natural Language Learning <\/i>, Oct 2018, Brussels, Belgium.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01791126\/document\" target=\"_blank\" rel=\"noopener\">Mixed batches and symmetric discriminators for GAN training<\/a> Thomas Lucas, Corentin Tallec, Jakob Verbeek, Yann Ollivier.\u00a0<i>ICML 2018 &#8211; International Conference on Machine Learning<\/i>, July 2018, Stockholm, Sweden<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01790879\/document\">Token-level and sequence-level loss smoothing for RNN language models.<\/a> Maha Elbayad, Laurent Besacier, Jakob Verbeek. \u00a0<em>ACL 2018 (long paper) &#8211; Annual Meeting of the Association for Computational Linguistics<\/em>, July 2018, Melbourne, Australia.<\/li>\n<li><a href=\"https:\/\/hal.archives-ouvertes.fr\/hal-01818092\/document\">Unsupervised Word Segmentation from Speech with Attention.<\/a> Pierre Godard, Marcely Zanon Boito, Lucas Ondel, Alexandre Berard, Fran\u00e7ois Yvon,\u00a0<span style=\"font-family: 'Source Sans Pro';\">Aline Villavicencio, Laurent Besacier.\u00a0<\/span>Interspeech 2018, Sep 2018, Hyderabad, India.<\/li>\n<li><a href=\"https:\/\/project.inria.fr\/decore\/files\/2017\/01\/main-1.pdf\">End-to-End Automatic Speech Translation of Audiobooks<\/a>. Alexandre B\u00e9rard, Laurent Besacier, Ali Can Kocabiyikoglu, Olivier Pietquin. ICASSP 2018 &#8211; IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada.<\/li>\n<li><a href=\"https:\/\/project.inria.fr\/decore\/files\/2017\/01\/20180214040820_904429_2819.pdf\">ASR Performance Prediction on Unseen Broadcast Programs using Convolutional Neural Networks.<\/a>\u00a0Zied Elloumi, Laurent Besacier, Olivier Galibert, Juliette Kahn, Benjamin Lecouteux.\u00a0ICASSP 2018 &#8211; IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada.<\/li>\n<li><a href=\"https:\/\/project.inria.fr\/decore\/files\/2017\/01\/main-2.pdf\">Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the &#8220;Speaking Rosetta&#8221; JSALT 2017 Workshop.<\/a> Odette Scharenborg, Laurent Besacier, et. al.\u00a0ICASSP 2018 &#8211; IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01540389\/document\" target=\"_blank\" rel=\"noopener\">FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis<\/a>, Nitika Verma, Edmond Boyer, Jakob Verbeek.\u00a0<i>CVPR &#8211; IEEE Conference on Computer Vision &amp; Pattern Recognition, June 2018, Salt Lake City, US<\/i>.<\/li>\n<li><a href=\"https:\/\/arxiv.org\/pdf\/1603.06470.pdf\">Frankenstein: Learning Deep Face Representations using Small Data<\/a>, Guosheng Hu, Member, IEEE, Xiaojiang Peng, Yongxin Yang, Timothy M. Hospedales, and Jakob Verbeek. <em>IEEE Transactions on Image Processing<\/em>,\u00a02018, 27 (1), pp. 293-303.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01652881\/document\" target=\"_blank\" rel=\"noopener\">Auxiliary Guided Autoregressive Variational Autoencoders,\u00a0<\/a>Thomas Lucas, Jakob Verbeek, European Conference on Machine Learning, 2018.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01757669\/document\" target=\"_blank\" rel=\"noopener\">Predicting Future Instance Segmentations by Forecasting Convolutional Features\u00a0<\/a>Pauline Luc, Camille Couprie, Yann Lecun, Jakob Verbeek. <em>European Conference on Computer Vision<\/em>, September 2018, Munich, Germany.<\/li>\n<\/ul>\n<p>2017<\/p>\n<ul>\n<li><a href=\"https:\/\/project.inria.fr\/decore\/files\/2017\/01\/unwritten2017-ASRUfinal.pdf\">Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models<\/a>. Marcely Zanon Boito, Alexandre B\u00e9rard, Aline Villavicencio, Laurent Besacier. \u00a0<em>IEEE Automatic Speech Recognition and Understanding (ASRU)<\/em>, Dec 2017, Okinawa, Japan.<\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1709.06053\">Coupled Ensembles of Neural Networks<\/a>, Anuvabh Dutt, Denis Pellerin, Georges Qu\u00e9not. <em>Preprint,\u00a0<\/em>2017.<\/li>\n<li><a href=\"https:\/\/hal.archives-ouvertes.fr\/hal-01590664v1\">Improving Hierarchical Image Classification with Merged CNN Architectures<\/a>, Anuvabh Dutt, Denis Pellerin, Georges Qu\u00e9not. <em>Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing<\/em>, June 2017, Firenze, Italy.<\/li>\n<li><a href=\"https:\/\/hal.archives-ouvertes.fr\/hal-01590672v1\">Improving Image Classification Using Coarse and Fine Labels<\/a>, Anuvabh Dutt, Denis Pellerin, Georges Qu\u00e9not. <em>Proceedings of the 2017 ACM International Conference on Multimedia Retrieval<\/em>, June 2017, Bucharest, Romania.<\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1703.10089\">Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs<\/a>, Yagmur G. Cinar, Hamid Mirisaee, Parantapa Goswami, Eric Gaussier, Ali Ait-Bachir, Vadim Strijov. <em>International Conference On Neural Information Processing<\/em>, November 2017, Guangzhou, China.<\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1703.07684\">Predicting Deeper into the Future of Semantic Segmentation<\/a>, Natalia Neverova, Pauline Luc, Camille Couprie, Jakob Verbeek, Yann LeCun.\u00a0<i>International Conference on Computer Vision<\/i>, October 2017, Venice, Italy.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01428963\" target=\"_blank\" rel=\"noopener noreferrer\">Areas of Attention for Image Captioning<\/a>,\u00a0Marco Pedersoli, Thomas Lucas, Cordelia Schmid, Jakob Verbeek.\u00a0<i>International Conference on Computer Vision<\/i>, October 2017, Venice, Italy.<\/li>\n<li><a href=\"https:\/\/project.inria.fr\/decore\/files\/2017\/01\/main.pdf\">LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task<\/a>,\u00a0Alexandre Berard, Olivier Pietquin, Laurent Besacier. <em>2nd Conference on Machine Translation\u00a0(WMT17)<\/em>,<em>\u00a0EMNLP 2017<\/em>, Copenhagen, Denmark.<\/li>\n<li><a href=\"https:\/\/project.inria.fr\/decore\/files\/2017\/01\/eacl2017.pdf\">Using Word Embedding for Cross-Language Plagiarism Detection<\/a>,\u00a0J. Ferrero, F. Agnes, L. Besacier, D. Schwab, <em>European Chapter of the Association for Computational Linguistics<\/em>, April 2017, Valencia, Spain.<\/li>\n<\/ul>\n<p>2016<\/p>\n<ul>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1612.01744\">Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation<\/a>,\u00a0Alexandre Berard, Olivier Pietquin, Christophe Servan, Laurent Besacier.\u00a0<i>NIPS Workshop on end-to-end learning \u00a0for speech and audio processing,\u00a0<\/i>Dec 2016, Barcelona, Spain.<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01374205\">Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks<\/a>,\u00a0Othman Zennaki, Nasredine Semmar, Laurent Besacier,\u00a0COLING 2016, Dec 2016, Osaka, Japan<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01359150v2\" target=\"_blank\" rel=\"noopener noreferrer\">Convolutional Neural Fabrics<\/a>,\u00a0Shreyas Saxena, Jakob Verbeek.\u00a0<i>Advances in Neural Information Processing Systems (NIPS)<\/i>, Dec 2016, Barcelona, Spain<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01398049\" target=\"_blank\" rel=\"noopener noreferrer\">Semantic Segmentation using Adversarial Networks<\/a>,\u00a0Pauline Luc, Camille Couprie, Soumith Chintala, Jakob Verbeek.\u00a0<i>NIPS Workshop on Adversarial Training<\/i>, Dec 2016, Barcelona, Spain<\/li>\n<li><a href=\"https:\/\/hal.inria.fr\/hal-01367455\" target=\"_blank\" rel=\"noopener noreferrer\">Heterogeneous Face Recognition with CNNs<\/a>,\u00a0Shreyas Saxena, Jakob Verbeek,\u00a0<i>ECCV TASK-CV 2016 Workshops<\/i>, Oct 2016, Amsterdam, Netherlands<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>2019 Adaptive Density Estimation for Generative Models. Thomas Lucas, Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari, Jakob Verbeek.\u00a0NeurIPS 2019 &#8211; Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image.\u00a0Roman Klokov, Jakob Verbeek, Edmond Boyer.\u00a0BMVC 2019 &#8211; British Machine\u2026<\/p>\n<p> <a class=\"continue-reading-link\" href=\"https:\/\/project.inria.fr\/decore\/publications\/\"><span>Continue reading<\/span><i class=\"crycon-right-dir\"><\/i><\/a> <\/p>\n","protected":false},"author":1053,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-74","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/pages\/74","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/users\/1053"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/comments?post=74"}],"version-history":[{"count":48,"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/pages\/74\/revisions"}],"predecessor-version":[{"id":249,"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/pages\/74\/revisions\/249"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/decore\/wp-json\/wp\/v2\/media?parent=74"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}