Journal and Conference Papers

2024

  1. Autoregressive GAN for Semantic Unconditional Head Motion Generation
    by L. Airale, X. Alameda-Pineda, S. Lathuilière, and D. Vaufreydaz
    in ACM Transactions on Multimedia Computing, Communications, and Applications
    [ bib | pdf | code | arxiv ]
    @article{Airale-TOMM-2024,
      title={Autoregressive GAN for Semantic Unconditional Head Motion Generation},
      author={Louis Airale and Xavier Alameda-Pineda and St\'ephane Lathuili\`ere and Dominique Vaufreydaz},
      year={2024},
      journal={ACM Transactions on Multimedia Computing, Communications, and Applications},
      arxiv={https://arxiv.org/abs/2211.00987},
      code={https://github.com/LouisBearing/UnconditionalHeadMotion},
      doi={10.1145/3635154},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Airale-TOMM-2024.pdf}
    }
  2. A weighted-variance variational autoencoder model for speech enhancement
    by A. Golmakani, M. Sadeghi, X. Alameda-Pineda, and R. Serizel
    in IEEE International Conference on Acoustics Speech and Signal Processing
    [ bib | pdf | arxiv ]
    @inproceedings{Golmakani-ICASSP-2024,
      title={A weighted-variance variational autoencoder model for speech enhancement},
      author={Ali Golmakani and Mostafa Sadeghi and Xavier Alameda-Pineda and Romain Serizel},
      year={2024},
      booktitle={IEEE International Conference on Acoustics Speech and Signal Processing},
      arxiv={https://arxiv.org/abs/2211.00990},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Golmakani-ICASSP-2024.pdf}
    }
  3. Unsupervised performance analysis of 3D face alignment with a statistically robust confidence test
    by M. Sadeghi, X. Alameda-Pineda, and R. Horaud
    in Neurocomputing
    [ bib | pdf | code | arxiv ]
    @article{Sadeghi-NeuroComputing-2024,
      title={Unsupervised performance analysis of 3D face alignment with a statistically robust confidence test},
      author={Mostafa Sadeghi and Xavier Alameda-Pineda and Radu Horaud},
      year={2024},
      journal={Neurocomputing},
      arxiv={https://arxiv.org/abs/2004.06550},
      code={https://gitlab.inria.fr/smostafa/upa3dfa},
      doi={10.1016/j.neucom.2023.126941},
      note={\url{https://team.inria.fr/robotlearn/upa3dfa/}},
      volume={564},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sadeghi-NeuroComputing-2024.pdf}
    }
  4. A Multimodal Dynamical Variational Autoencoder for Audiovisual Speech Representation Learning
    by S. Sadok, S. Leglaive, L. Girin, X. Alameda-Pineda, and R. Séguier
    in Neural Networks
    [ bib | pdf | code | arxiv ]
    @article{Sadok-NeuralNetworks-2024,
      title={A Multimodal Dynamical Variational Autoencoder for Audiovisual Speech Representation Learning},
      author={Samir Sadok and Simon Leglaive and Laurent Girin and Xavier Alameda-Pineda and Renaud S\'eguier},
      year={2024},
      journal={Neural Networks},
      arxiv={https://arxiv.org/abs/2305.03582},
      code={https://github.com/samsad35/multimodal_vae},
      note={\url{https://samsad35.github.io/site-mdvae/}},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sadok-NeuralNetworks-2024.pdf}
    }
  5. Robust Audio-Visual Contrastive Learning for Proposal-based Self-supervised Sound Source Localization in Videos
    by H. Xuan, Z. Wu, J. Yang, B. Jiang, L. Luo, X. Alameda-Pineda, and Y. Yan
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf ]
    @article{Xuan-TPAMI-2024,
      title={Robust Audio-Visual Contrastive Learning for Proposal-based Self-supervised Sound Source Localization in Videos},
      author={Hanyu Xuan and Zhiliang Wu and Jian Yang and Bo Jiang and Lei Luo and Xavier Alameda-Pineda and Yan Yan},
      year={2024},
      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
      arxiv={},
      code={},
      doi={},
      note={},
      pages={},
      volume={},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xuan-TPAMI-2024.pdf}
    }

2023

  1. Variational Meta Reinforcement Learning for Social Robotics
    by A. Ballou, X. Alameda-Pineda, and C. Reinke
    in Applied Intelligence
    [ bib | pdf | arxiv ]
    @article{Ballou-APIN-2023,
      title={Variational Meta Reinforcement Learning for Social Robotics},
      author={Anand Ballou and Xavier Alameda-Pineda and Chris Reinke},
      year={2023},
      journal={Applied Intelligence},
      arxiv={https://arxiv.org/abs/2206.03211},
      pages={27249-27268},
      volume={53},
      doi={10.1007/s10489-023-04691-5},  
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ballou-APIN-2023.pdf}
    }
  2. On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
    by T. D. Min, M. Mancini, K. Alahari, X. Alameda-Pineda, and E. Ricci
    in International Conference on Computer Vision Workshops
    [ bib | code | arxiv ]
    @inproceedings{DeMin-ICCVW-2023,
      title={On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers},
      keywords={workshop},
      booktitle={International Conference on Computer Vision Workshops},
      author={Thomas De Min and Massimiliano Mancini and Karteek Alahari and Xavier Alameda-Pineda and Elisa Ricci},
      year={2023},
      code={https://github.com/tdemin16/Continual-LayerNorm-Tuning},
      arxiv={https://arxiv.org/abs/2308.09610},
    }
  3. Motion-DVAE: Unsupervised learning for fast human motion denoising
    by G. Fiche, S. Leglaive, X. Alameda-Pineda, and R. Séguier
    in ACM SIGGRAPH Conference on Motion, Interaction and Games
    [ bib | pdf | code | arxiv ]
    @inproceedings{Fiche-MIG-2023,
      title={{Motion-DVAE}: Unsupervised learning for fast human motion denoising},
      author={Guénolé Fiche and Simon Leglaive and Xavier Alameda-Pineda and Renaud Séguier},
      year={2023},
      booktitle={ACM SIGGRAPH Conference on Motion, Interaction and Games},
      arxiv={https://arxiv.org/abs/2306.05846},
      code={https://g-fiche.github.io/research-pages/motiondvae/},
      doi={10.1145/3623264.3624454},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Fiche-MIG-2023.pdf}
    }
  4. Semi-supervised learning made simple with self-supervised clustering
    by E. Fini, P. Astolfi, K. Alahari, X. Alameda-Pineda, J. Mairal, M. Nabi, and E. Ricci
    in IEEE/CVF Conference on Computer Vision and Pattern Recognition
    [ bib | pdf | arxiv ]
    @inproceedings{Fini-CVPR-2023,
      title={Semi-supervised learning made simple with self-supervised clustering},
      author={Enrico Fini and Pietro Astolfi and Karteek Alahari and Xavier Alameda-Pineda and Julien Mairal and Moin Nabi and Elisa Ricci},
      booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      year={2023},
        pages={3187-3197},
      arxiv={https://arxiv.org/abs/2306.07483},
      doi={10.1109/CVPR52729.2023.00311},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Fini-CVPR-2023.pdf}
    }
  5. Back to MLP: A Simple Baseline for Human Motion Prediction
    by W. Guo, Y. Du, X. Shen, V. Lepetit, X. Alameda-Pineda, and F. Moreno-Noguer
    in IEEE Winter Conference on Applications of Computer Vision
    [ bib | pdf | code | arxiv ]
    @inproceedings{Guo-WACV-2023,
      TITLE = {{Back to MLP: A Simple Baseline for Human Motion Prediction}},
      AUTHOR = {Guo, Wen and Du, Yuming and Shen, Xi and Lepetit, Vincent and Alameda-Pineda, Xavier and Moreno-Noguer, Francesc},
      BOOKTITLE = {{IEEE Winter Conference on Applications of Computer Vision}},
      YEAR = {2023},
      code={https://github.com/dulucas/siMLPe},
      doi={10.1109/WACV56688.2023.00479},
      arxiv={https://arxiv.org/abs/2207.01567},
      pages={4809-4819},
      code={https://github.com/dulucas/siMLPe},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Guo-WACV-2023.pdf}
    }
  6. Expression-preserving face frontalization improves visually assisted speech processing
    by Z. Kang, M. Sadeghi, R. Horaud, and X. Alameda-Pineda
    in International Journal of Computer Vision
    [ bib | pdf | arxiv ]
    @article{Kang-IJCV-2023,
      TITLE = {Expression-preserving face frontalization improves visually assisted speech processing},
      AUTHOR = {Kang, Zhiqi and Sadeghi, Mostafa and Horaud, Radu and Alameda-Pineda, Xavier},
      JOURNAL = {International Journal of Computer Vision},
      YEAR = {2023},
        doi={10.1007/s11263-022-01742-1},
      arxiv={https://arxiv.org/abs/2204.02810},
        volume={131},
      issue={5},
      pages={1122-1140},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Kang-IJCV-2023.pdf}
    }
  7. Speech Modeling with a Hierarchical Transformer Dynamical VAE
    by X. Lin, S. Leglaive, L. Girin, and X. Alameda-Pineda
    in IEEE International Conference on Audio, Speech and Signal Processing
    [ bib | pdf ]
    @inproceedings{Lin-ICASSP-2023,
      title={Speech Modeling with a Hierarchical Transformer Dynamical {VAE}},
      author={Xiaoyu Lin and Simon Leglaive and Laurent Girin and Xavier Alameda-Pineda},
      booktitle={IEEE International Conference on Audio, Speech and Signal Processing},
      year={2023},
      doi={10.1109/ICASSP49357.2023.10096751},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Lin-ICASSP-2023.pdf}
    }
  8. Unsupervised speech enhancement with deep dynamical generative speech and noise models
    by X. Lin, S. Leglaive, L. Girin, and X. Alameda-Pineda
    in Interspeech
    [ bib | pdf | arxiv ]
    @inproceedings{Lin-Interspeech-2023,
      title={Unsupervised speech enhancement with deep dynamical generative speech and noise models},
      author={Xiaoyu Lin and Simon Leglaive and Laurent Girin and Xavier Alameda-Pineda},
      booktitle={Interspeech},
      year={2023},
      pages={5102-5106},
      doi={10.21437/Interspeech.2023-232},
      arxiv={https://arxiv.org/abs/2306.07820},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Lin-Interspeech-2023.pdf}
    }
  9. Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
    by X. Lin, L. Girin, and X. Alameda-Pineda
    in Transactions on Machine Learning Research
    [ bib | pdf | code | arxiv ]
    @article{Lin-TMLR-2023,
      title={Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation},
      author={Xiaoyu Lin and Laurent Girin and Xavier Alameda-Pineda},
      year={2023},
      journal={Transactions on Machine Learning Research},
      arxiv={https://arxiv.org/abs/2312.04167},
      code={https://github.com/linxiaoyu1/MixDVAE},
      note={\url{https://openreview.net/forum?id=sbkZKBVC31}},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Lin-TMLR-2023.pdf}
    }
  10. Successor Feature Representations
    by C. Reinke and X. Alameda-Pineda
    in Transactions on Machine Learning Research
    [ bib | pdf | code | arxiv ]
    @article{Reinke-TMLR-2023,
      title={Successor Feature Representations},
      author={Chris Reinke and Xavier Alameda-Pineda},
      year={2023},
      journal={Transactions on Machine Learning Research},
      arxiv={https://arxiv.org/abs/2110.15701},
      code={https://gitlab.inria.fr/robotlearn/sfr_learning},
      note={\url{https://openreview.net/forum?id=MTFf1rDDEI}},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Reinke-TMLR-2023.pdf}
    }
  11. Learning and controlling the source-filter representation of speech with a variational autoencoder
    by S. Sadok, S. Leglaive, L. Girin, X. Alameda-Pineda, and R. Séguier
    in Speech Communication
    [ bib | pdf | code | arxiv ]
    @article{Sadok-SpeechCom-2023,
      title={Learning and controlling the source-filter representation of speech with a variational autoencoder},
      author={Sadok, Samir and Leglaive, Simon and Girin, Laurent and Alameda-Pineda, Xavier and S\'eguier, Renaud},
      journal={Speech Communication},
      arxiv={https://arxiv.org/abs/2204.07075},
      year={2023},
      month={3},
      pages={53-65},
      volume={148},
      doi={10.1016/j.specom.2023.02.005},
      code={https://github.com/samsad35/source-filter-vae},
      note={\url{https://samsad35.github.io/site-sfvae/}},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sadok-SpeechCom-2023.pdf}
    }

2022

  1. SocialInteractionGAN: Multi-person Interaction Sequence Generation
    by L. Airale, D. Vaufreydaz, and X. Alameda-Pineda
    in IEEE/ACM Transactions on Affective Computing
    [ bib | pdf | arxiv ]
    @article{Airale-TAFFC-2022,
      title={SocialInteractionGAN: Multi-person Interaction Sequence Generation},
      author={Airale, Louis and Vaufreydaz, Dominique and Alameda-Pineda, Xavier},
      journal={IEEE/ACM Transactions on Affective Computing},
      year={2022},
      doi={10.1109/TAFFC.2022.3171719},
      arxiv={https://arxiv.org/abs/2103.05916},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Airale-TAFFC-2022.pdf}
    }
  2. M4MM’22: 1st International Workshop on Methodologies for Multimedia
    by X. Alameda-Pineda, Q. Jin, V. Oria, and L. Toni
    in ACM International Conference on Multimedia
    [ bib | pdf ]
    @inproceedings{Alameda-M4MM-2022,
    title={{M4MM}'22: 1st International Workshop on Methodologies for Multimedia},
    author={Xavier Alameda-Pineda and Qin Jin and Vincent Oria and Laura Toni},
    booktitle={ACM International Conference on Multimedia},
    address={Lisbon, Portugal},
    year={2022},
    doi={10.1145/3503161.3554769},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-M4MM-2022.pdf}
    }
  3. Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders
    by X. Bie, S. Leglaive, X. Alameda-Pineda, and L. Girin
    in IEEE/ACM Transactions on Audio, Signal and Language Processing
    [ bib | pdf | code | arxiv ]
    @article{Bie-TASLP-2022,
      title={Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders},
      author={Bie, Xiaoyu and Leglaive, Simon and Alameda-Pineda, Xavier and Girin, Laurent},
      journal={IEEE/ACM Transactions on Audio, Signal and Language Processing},
      year=2022,
      doi={10.1109/TASLP.2022.3207349},
      code={https://github.com/XiaoyuBIE1994/DVAE_SE},
      arxiv={https://arxiv.org/abs/2106.12271},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Bie-TASLP-2022.pdf}
    }
  4. Self-supervised models are continual learners
    by E. Fini, V. T. G. da Costa, X. Alameda-Pineda, E. Ricci, K. Alahari, and J. Mairal
    in IEEE/CVF Conference on Computer Vision and Pattern Recognition
    [ bib | pdf | code | arxiv ]
    @inproceedings{Fini-CVPR-2022,
      title={Self-supervised models are continual learners},
      author={Fini, Enrico and da Costa, Victor G Turrisi and Alameda-Pineda, Xavier and Ricci, Elisa and Alahari, Karteek and Mairal, Julien},
      booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      pages={9621--9630},
      year={2022},
      code={https://github.com/DonkeyShot21/cassle},
      arxiv={https://arxiv.org/abs/2112.04215},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Fini-CVPR-2022.pdf}
    }
  5. Dynamical Variational Autoencoders: A Comprehensive Review
    by L. Girin, S. Leglaive, X. Bie, J. Diard, T. Hueber, and X. Alameda-Pineda
    in Foundations and Trends in Machine Learning
    [ bib | pdf | code | arxiv ]
    @article{Girin-FnT-2021,
      title={Dynamical Variational Autoencoders: A Comprehensive Review},
      author={Girin, Laurent and Leglaive, Simon and Bie, Xiaoyu and Diard, Julien and Hueber, Thomas and Alameda-Pineda, Xavier},
      arxiv={https://arxiv.org/abs/2008.12595},
      journal={Foundations and Trends in Machine Learning},
      code={https://github.com/XiaoyuBIE1994/DVAE-speech},
      number={15},
      volume={1-2},
      doi={10.1561/2200000089},
      year={2022},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Girin-FnT-2021.pdf}
    }
  6. Les auto-encodeurs variationnels dynamiques et leur application à la modélisation de spectrogrammes de parole
    by L. Girin, X. Bie, S. Leglaive, T. Hueber, and X. Alameda-Pineda
    in XXXIVe Journées d’études sur la Parole
    [ bib | pdf ]
    @inproceedings{Girin-JEP-2022,
    title = {Les auto-encodeurs variationnels dynamiques et leur application à la modélisation de spectrogrammes de parole},
    author={Laurent Girin and Xiaoyu Bie and Simon Leglaive and Thomas Hueber and Xavier Alameda-Pineda},
    year={2022},
    booktitle={XXXIVe Journ\'ees d'\'Etudes sur la Parole},
    doi={10.21437/JEP.2022-69},
    keywords={french},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Girin-JEP-2022.pdf}
    }
  7. Multi-Person Extreme Motion Prediction with Cross-Interaction Attention
    by W. Guo, X. Bie, X. Alameda-Pineda, and F. Moreno
    in IEEE/CVF Conference on Computer Vision and Pattern Recognition
    [ bib | pdf | code | arxiv ]
    @inproceedings{Guo-CVPR-2022,
      title={Multi-Person Extreme Motion Prediction with Cross-Interaction Attention},
      author={Guo, Wen and Bie, Xiaoyu and Alameda-Pineda, Xavier and Moreno, Francesc},
      year={2022},
      booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      doi={10.1109/CVPR52688.2022.01271},
      code={https://github.com/GUO-W/MultiMotion},
      arxiv={https://arxiv.org/abs/2105.08825},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Guo-CVPR-2022.pdf}
    }
  8. The impact of removing head movements on audio-visual speech enhancement
    by Z. Kang, M. Sadeghi, R. Horaud, X. Alameda-Pineda, J. Donley, and A. Kumar
    in IEEE International Conference on Acoustics, Speech and Signal Processing
    [ bib | pdf | arxiv ]
    @inproceedings{Kang-ICASSP-2022,
      title={The impact of removing head movements on audio-visual speech enhancement},
      author={Kang, Zhiqi and Sadeghi, Mostafa and Horaud, Radu and Alameda-Pineda, Xavier and Donley, Jacob and Kumar, Anurag},
      booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing},
      pages={7302--7306},
      year={2022},
      arxiv={https://arxiv.org/abs/2202.00538},
      doi={10.1109/ICASSP43922.2022.9746401},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Kang-ICASSP-2022.pdf}
    }
  9. A Proposal-based Paradigm for Self-supervised Sound Source Localization in Videos
    by H. Xuan, Z. Wu, J. Yang, Y. Yan, and X. Alameda-Pineda
    in IEEE/CVF Conference on Computer Vision and Pattern Recognition
    [ bib | pdf | arxiv ]
    @inproceedings{Xuan-CVPR-2022,
      author={Hanyu Xuan and Zhiliang Wu and Jian Yang and Yan Yan and Xavier Alameda-Pineda},
      title={A Proposal-based Paradigm for Self-supervised Sound Source Localization in Videos},
      booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      year={2022},
      doi={10.1109/CVPR52688.2022.00110},
      arxiv={https://openaccess.thecvf.com/content/CVPR2022/papers/Xuan_A_Proposal-Based_Paradigm_for_Self-Supervised_Sound_Source_Localization_in_Videos_CVPR_2022_paper.pdf},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xuan-CVPR-2022.pdf}
    }
  10. Active Contrastive Set Mining for Robust Audio-Visual Instance Discrimination
    by H. Xuan, Y. Xu, S. Chen, Z. Wu, J. Yang, Y. Yan, and X. Alameda-Pineda
    in International Joint Conference on Artificial Intelligence
    [ bib | pdf | arxiv ]
    @inproceedings{Xuan-IJCAI-2022,
      author={Hanyu Xuan and Yihong Xu and Shuo Chen and Zhiliang Wu and Jian Yang and Yan Yan and Xavier Alameda-Pineda},
      title={Active Contrastive Set Mining for Robust Audio-Visual Instance Discrimination},
      booktitle={International Joint Conference on Artificial Intelligence},
      year={2022},
      doi={10.24963/ijcai.2022/506},
      arxiv={https://www.ijcai.org/proceedings/2022/0506.pdf},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xuan-IJCAI-2022.pdf}
    }
  11. TransCenter: Transformers with Dense Queries for Multiple-Object Tracking
    by Y. Xu, Y. Ban, G. Delorme, C. Gan, D. Rus, and X. Alameda-Pineda
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf | code | arxiv ]
    @article{Xu-TPAMI-2022,
      title={TransCenter: Transformers with Dense Queries for Multiple-Object Tracking},
      author={Xu, Yihong and Ban, Yutong and Delorme, Guillaume and Gan, Chuang and Rus, Daniela and Alameda-Pineda, Xavier},
      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
      arxiv={arXiv preprint arXiv:2103.15145},
      doi={10.1109/TPAMI.2022.3225078},
      code={https://github.com/yihongXU/TransCenter},
      year={2022},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-TPAMI-2022.pdf}
    }
  12. Continual Attentive Fusion for Incremental Learning in Semantic Segmentation
    by G. Yang, E. Fini, D. Xu, P. Rota, M. Ding, T. Hao, X. Alameda-Pineda, and E. Ricci
    in IEEE Transactions on Multimedia
    [ bib | pdf | code | arxiv ]
    @article{Yang-TMM-2022,
      title={Continual Attentive Fusion for Incremental Learning in Semantic Segmentation},
      author={Yang, Guanglei and Fini, Enrico and Xu, Dan and Rota, Paolo and Ding, Mingli and Hao, Tang and Alameda-Pineda, Xavier and Ricci, Elisa},
      journal={IEEE Transactions on Multimedia},
      year={2022},
      pages={3841-3854},
      volume={25},
      code={https://github.com/ygjwd12345/CAF},
      arxiv={https://arxiv.org/abs/2202.00432},
      doi={10.1109/TMM.2022.3167555},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Yang-TMM-2022.pdf}
    }
  13. Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation
    by G. Yang, E. Fini, D. Xu, P. Rota, M. Ding, M. Nabi, X. Alameda-Pineda, and E. Ricci
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf | code | arxiv ]
    @article{Yang-TPAMI-2022,
      title={Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation},
      author={Yang, Guanglei and Fini, Enrico and Xu, Dan and Rota, Paolo and Ding, Mingli and Nabi, Moin and Alameda-Pineda, Xavier and Ricci, Elisa},
      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
      year={2022},
      code={https://github.com/ygjwd12345/UCD},
      arxiv={https://arxiv.org/abs/2203.14098},
      doi={10.1109/TPAMI.2022.3163806},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Yang-TPAMI-2022.pdf}
    }

2021

  1. Variational Inference and Learning of Piecewise-linear Dynamical Systems
    by X. Alameda-Pineda, V. Drouard, and R. Horaud
    in IEEE Transactions on Neural Networks and Learning Systems
    [ bib | pdf | arxiv ]
    @article{Alameda-TNNLS-2021,
      title={Variational Inference and Learning of Piecewise-linear Dynamical Systems},
      author={Xavier Alameda-Pineda and Vincent Drouard and Radu Horaud},
      year={2021},
      journal={IEEE Transactions on Neural Networks and Learning Systems},
      doi={10.1109/TNNLS.2021.3054407},
      arxiv={https://arxiv.org/abs/2006.01668},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-TNNLS-2021.pdf}
    }
  2. A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
    by X. Bie, L. Girin, S. Leglaive, T. Hueber, and X. Alameda-Pineda
    in ISCA Interspeech
    [ bib | pdf | code | arxiv ]
    @inproceedings{Bie-Interspeech-2021,
      title={A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling},
      author={Bie, Xiaoyu and Girin, Laurent and Leglaive, Simon and Hueber, Thomas and Alameda-Pineda, Xavier},
      booktitle={ISCA Interspeech},
      year={2021},
      doi={10.21437/Interspeech.2021-256},
      code={https://github.com/XiaoyuBIE1994/DVAE},
      arxiv={https://arxiv.org/abs/2106.06500},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Bie-Interspeech-2021.pdf}
    }
  3. Successor Feature Neural Episodic Control
    by D. Emukpere, X. Alameda-Pineda, and C. Reinke
    in Fifth Workshop on Meta-Learning at the Conference on Neural Information Processing Systems
    [ bib | pdf | arxiv ]
    @inproceedings{Emukpere-NeurIPSW-2021,
      title={Successor Feature Neural Episodic Control},
      author={Emukpere, David and Alameda-Pineda, Xavier and Reinke, Chris},
      booktitle={Fifth Workshop on Meta-Learning at the Conference on Neural Information Processing Systems},
      keywords={workshop},
      year={2021},
      arxiv={https://arxiv.org/abs/2111.03110},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Emukpere-NeurIPSW-2021.pdf}
    }
  4. PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation
    by W. Guo, E. Corona, F. Moreno-Noguer, and X. Alameda-Pineda
    in IEEE Winter Conference on Applications of Computer Vision
    [ bib | pdf | code | arxiv ]
    @inproceedings{Guo-WACV-2021,
    title={PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation},
    author={Wen Guo and Enric Corona and Francesc Moreno-Noguer and Xavier Alameda-Pineda},
    year=2021,
    booktitle={IEEE Winter Conference on Applications of Computer Vision},
    arxiv={https://arxiv.org/abs/2010.05302},
    doi={10.1109/WACV48630.2021.00284},
    code={https://github.com/GUO-W/PI-Net},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Guo-WACV-2021.pdf}
    }
  5. Deep Variational Generative Models for Audio-visual Speech Separation
    by V. Nguyen, M. Sadeghi, E. Ricci, and X. Alameda-Pineda
    in IEEE Workshop on Machine Learning for Signal Processing
    [ bib | pdf | arxiv ]
    @inproceedings{Nguyen-MLSP-2021,
      title={Deep Variational Generative Models for Audio-visual Speech Separation},
      author={Nguyen, Viet-Nhat and Sadeghi, Mostafa and Ricci, Elisa and Alameda-Pineda, Xavier},
      booktitle={IEEE Workshop on Machine Learning for Signal Processing},
      arxiv={https://arxiv.org/abs/2008.07191},
      year={2021},
      address={Queensland, Australia},
      doi={10.1109/MLSP52302.2021.9596406},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Nguyen-MLSP-2021.pdf}
    }
  6. Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement
    by M. Sadeghi and X. Alameda-Pineda
    in IEEE International Conference on Audio, Speech and Signal Processing
    [ bib | pdf | arxiv ]
    @inproceedings{Sadeghi-ICASSP-2021,
      title={Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement},
      author={Sadeghi, Mostafa and Alameda-Pineda, Xavier},
      booktitle={IEEE International Conference on Audio, Speech and Signal Processing},
      year={2021},
      doi={10.1109/ICASSP39728.2021.9414097},
      arxiv={https://arxiv.org/abs/2102.04144},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sadeghi-ICASSP-2021.pdf}
    }

2020

  1. FATE/MM’20: 2nd International Workshop on Fairness, Accountability, Transparency and Ethics
    by X. Alameda-Pineda, M. Redi, J. Otterbacher, N. Sebe, and S. Chang
    in ACM International Conference on Multimedia
    [ bib | pdf ]
    @inproceedings{Alameda-FATEMM-2020,
    author={Xavier Alameda-Pineda and Miriam Redi and Jahna Otterbacher and Nicu Sebe and Shih-Fu Chang},
    title={{FATE/MM}'20: 2nd International Workshop on Fairness, Accountability, Transparency and Ethics},
    year={2020},
    booktitle={ACM International Conference on Multimedia},
    doi={10.1145/3394171.3421896},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-FATEMM-2020.pdf}
    }
  2. Variational Bayesian Inference for Audio-Visual Tracking of Multiple Speakers
    by Y. Ban, X. Alameda-Pineda, L. Girin, and R. Horaud
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf | arxiv ]
    @article{Ban-TPAMI-2020,
      title={Variational Bayesian Inference for Audio-Visual Tracking of Multiple Speakers},
      author={Yutong Ban and Xavier Alameda-Pineda and Laurent Girin and Radu Horaud},
      year={2020},
      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
      doi={10.1109/TPAMI.2019.2953020},
      arxiv={https://arxiv.org/abs/1809.10961},
      volume={43},
      number={5},
            pages={1761-1776},
    
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ban-TPAMI-2020.pdf}
    }
  3. CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
    by G. Delorme, Y. Xu, S. Lathuilière, R. Horaud, and X. Alameda-Pineda
    in IEEE International Conference on Pattern Recognition
    [ bib | pdf | arxiv ]
    @inproceedings{Delorme-ICPR-2020,
    title={CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification},
    author={Guillaume Delorme and Yihong Xu and Stephane Lathuili\`{e}re and Radu Horaud and Xavier Alameda-Pineda},
    year=2020,
    doi={10.1109/ICPR48806.2021.9412431},
    booktitle={IEEE International Conference on Pattern Recognition},
    arxiv={https://arxiv.org/abs/1904.01308},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Delorme-ICPR-2020.pdf}
    }
  4. ODA-Track: Online Deep Appearance for Robotic Multiple Person Tracking
    by G. Delorme, Y. Ban, G. Sarrazin, and X. Alameda-Pineda
    in IAPR International Conference on Pattern Recognition Workshops
    [ bib | pdf ]
    @inproceedings{Delorme-ICPRW-2020,
    author={Guillaume Delorme and Yutong Ban and Guillaume Sarrazin and Xavier Alameda-Pineda},
    title={ODA-Track: Online Deep Appearance for Robotic Multiple Person Tracking},
    year={2020},
    keywords={workshop},
    booktitle={IAPR International Conference on Pattern Recognition Workshops},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Delorme-ICRPW-2020.pdf}
    }
  5. A Recurrent Variational Autoencoder for Speech Enhancement
    by S. Leglaive, X. Alameda-Pineda, L. Girin, and R. Horaud
    in IEEE International Conference on Audio, Speech and Signal Processing
    [ bib | pdf | code | arxiv ]
    @inproceedings{Leglaive-ICASSP-2020,
    title={A Recurrent Variational Autoencoder for Speech Enhancement},
    author={Simon Leglaive and Xavier Alameda-Pineda and Laurent Girin and Radu Horaud},
    booktitle={IEEE International Conference on Audio, Speech and Signal Processing},
    year={2020},
    doi={10.1109/ICASSP40776.2020.9053164},
    code={https://gitlab-research.centralesupelec.fr/sleglaive/icassp-2020-se-rvae},
    arxiv={https://arxiv.org/abs/1910.10942},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Leglaive-ICASSP-2020.pdf}
    }
  6. Describe What to Change: A Text-guided Unsupervised Image-to-image Translation Approach
    by Y. Liu, M. D. Nadai, D. Cai, H. Li, X. Alameda-Pineda, N. Sebe, and B. Lepri
    in ACM International Conference on Multimedia
    [ bib | pdf ]
    @inproceedings{Liu-ACMMM-2020,
    author={Yahui Liu and Marco De Nadai and Deng Cai and Huayang Li and Xavier Alameda-Pineda and
    Nicu Sebe and Bruno Lepri},
    title={Describe What to Change: A Text-guided Unsupervised Image-to-image Translation Approach
    },
    year={2020},
    booktitle={ACM International Conference on Multimedia},
    doi={10.1145/3394171.3413505},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Liu-ACMMM-2020.pdf}
    }
  7. Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders
    by M. Sadeghi and X. Alameda-Pineda
    in IEEE International Conference on Audio, Speech and Signal Processing
    [ bib | pdf | code | arxiv ]
    @inproceedings{Sadeghi-ICASSP-2020,
    author={Mostafa Sadeghi and Xavier Alameda-Pineda},
    title={Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders},
    booktitle={IEEE International Conference on Audio, Speech and Signal Processing},
    address={Barcelona, Spain},
    year={2020},
    doi={10.1109/ICASSP40776.2020.9053730},
    code={https://github.com/msaadeghii/avse-vae},
    arxiv={https://arxiv.org/abs/1911.03930},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sadeghi-ICASSP-2020.pdf}
    }
  8. Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders
    by M. Sadeghi, S. Leglaive, X. Alameda-Pineda, L. Girin, and R. Horaud
    in IEEE Transactions on Audio, Language and Signal Processing
    [ bib | pdf | code | arxiv ]
    @article{Sadeghi-TASLP-2020,
    title={Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders},
    author={Mostafa Sadeghi and Simon Leglaive and Xavier Alameda-Pineda and Laurent Girin and Radu Horaud},
    year={2020},
    journal={IEEE Transactions on Audio, Language and Signal Processing},
    code={https://github.com/msaadeghii/avse-vae},
    doi={10.1109/TASLP.2020.3000593},
    arxiv={https://arxiv.org/abs/1908.02590},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sadeghi-TASLP-2020.pdf}
    }
  9. Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
    by M. Sadeghi and X. Alameda-Pineda
    in IEEE Transactions on Signal Processing
    [ bib | pdf | code | arxiv ]
    @article{Sadeghi-TSP-2020,
    title={Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement},
    author={Mostafa Sadeghi and Xavier Alameda-Pineda},
    year={2020},
    arxiv={https://arxiv.org/abs/1912.10647},
    journal={IEEE Transactions on Signal Processing},
    number={69},
    code={https://github.com/msaadeghii/avse-vae},
    pages={1899-1909},
    doi={10.1109/TSP.2021.3066038},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sadeghi-TSP-2020.pdf}
    }
  10. Learning How to Smile: Expression Video Generation with Conditional Adversarial Recurrent Nets
    by W. Wang, X. Alameda-Pineda, D. Xu, E. Ricci, and N. Sebe
    in IEEE Transactions on Multimedia
    [ bib | pdf ]
    @article{Wang-TMM-2020,
    title={Learning How to Smile: Expression Video Generation with Conditional Adversarial Recurrent Nets},
    author={Wei Wang and Xavier Alameda-Pineda and Dan Xu and Elisa Ricci and Nicu Sebe},
    journal={IEEE Transactions on Multimedia},
    year={2020},
    doi={10.1109/TMM.2019.2963621},
    volume={22},
    number={11},
    pages={2808--2819},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Wang-TMM-2020.pdf}
    }
  11. How to Train Your Deep Multi-Object Tracker
    by Y. Xu, A. Osep, Y. Ban, R. Horaud, L. Leal-Taixé, and X. Alameda-Pineda
    in IEEE International Conference on Computer Vision and Pattern Recognition
    [ bib | pdf | code | arxiv ]
    @inproceedings{Xu-CVPR-2020,
    title={How to Train Your Deep Multi-Object Tracker},
    author={Yihong Xu and Aljosa Osep and Yutong Ban and Radu Horaud and Laura Leal-Taixé and Xavier Alameda-Pineda},
    year={2020},
    arxiv={https://arxiv.org/abs/1906.06618},
    code={https://github.com/yihongXU/deepMOT},
    booktitle={IEEE International Conference on Computer Vision and Pattern Recognition},
    doi={10.1109/CVPR42600.2020.00682},
    address={Seatle,USA},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-CVPR-2020.pdf}
    }
  12. Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction
    by D. Xu, X. Alameda-Pineda, W. Ouyang, E. Ricci, X. Wang, and N. Sebe
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf ]
    @article{Xu-TPAMI-2020,
      author={Dan Xu and Xavier Alameda-Pineda and Wanly Ouyang and Elisa Ricci and Xiaogang Wang and Nicu Sebe},
      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
      title={Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction}, 
      year={2020},
      doi={10.1109/TPAMI.2020.3043781},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-TPAMI-2020.pdf}
    }

2019

  1. Audio-Visual Variational Fusion for Multi-Person Tracking with Robots
    by X. Alameda-Pineda, S. Arias, Y. Ban, G. Delorme, L. Girin, R. Horaud, X. Li, B. Mourgue, and G. Sarrazin
    in ACM Multimedia
    [ bib | pdf ]
    @inproceedings{Alameda-ACMMM-2019,
    title={Audio-Visual Variational Fusion for Multi-Person Tracking with Robots},
    author={Xavier Alameda-Pineda and Soraya Arias and Yutong Ban and Guillaume Delorme and Laurent Girin and Radu Horaud and Xiaofei Li and Bastien Mourgue and Guillaume Sarrazin},
    booktitle={ACM Multimedia},
    year=2019,
    address={Nice, France},
    doi={10.1145/3343031.3350590},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-ACMMM-2019.pdf}
    }
  2. FAT/MM’19: 1st International Workshop on Fairness, Accountability, and Transparency in MultiMedia
    by X. Alameda-Pineda, M. Redi, E. Celis, N. Sebe, and S. Chang
    in ACM International Conference on Multimedia
    [ bib | pdf ]
    @inproceedings{Alameda-FATMM-2019,
    title={{FAT/MM'19}: 1st International Workshop on Fairness, Accountability, and Transparency in MultiMedia},
    author={Xavier Alameda-Pineda and Miriam Redi and Elisa Celis and Nicu Sebe and Shih-Fu Chang},
    booktitle={ACM International Conference on Multimedia},
    year={2019},
    address={Nice, France},
    doi={10.1145/3343031.3350555},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-FATMM-2019.pdf}
    }
  3. Tracking Multiple Audio Sources with the Von Mises Distribution and Variational EM
    by Y. Ban, X. Alameda-Pineda, C. Evers, and R. Horaud
    in IEEE Signal Processing Letters
    [ bib | pdf ]
    @article{Ban-SPL-2019,
      title={Tracking Multiple Audio Sources with the Von Mises Distribution and Variational EM},
      author={Y. Ban and X. Alameda-Pineda and C. Evers and R. Horaud},
      journal={IEEE Signal Processing Letters},
      year={2019},
      volume={26},
        number={6},
        pages={798--802},
      doi={10.1109/LSP.2019.2908376},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ban-SPL-2019.pdf}
    }
  4. Predicting Media Memorability Task at MediaEval 2019
    by M. G. Constantin, B. Ionescu, C. Demarty, N. Q. Duong, X. Alameda-Pineda, and M. Sjöberg
    in MediaEval 2019 Workshop
    [ bib | pdf ]
    @inproceedings{Constantin-MediaEval-2019,
      title={Predicting Media Memorability Task at MediaEval 2019},
      author={Mihai Gabriel Constantin and Bogdan Ionescu and Claire-H\'el\`ene Demarty and Ngoc QK Duong and Xavier Alameda-Pineda and Mats Sj\"oberg},
      year={2019},
      booktitle={MediaEval 2019 Workshop},
      keywords={workshop},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Constantin-MediaEval-2019.pdf}
    }
  5. A Comprehensive Analysis of Deep Regression
    by S. Lathuilière, P. Mesejo, X. Alameda-Pineda, and R. Horaud
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf | code | arxiv ]
    @article{Lathuiliere-TPAMI-2019,
      title={A Comprehensive Analysis of Deep Regression},
      author={St\`ephane Lathuili\`ere and Pablo Mesejo and Xavier Alameda-Pineda and Radu Horaud},
      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
      year={2019},
      arxiv={https://arxiv.org/abs/1803.08450},
      code={https://github.com/Stephlat/DeepRegression},
      doi={10.1109/TPAMI.2019.2910523},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Lathuiliere-TPAMI-2019.pdf}
    }
  6. Online Localization and Tracking of Multiple Moving Speakers in Reverberant Environment
    by X. Li, Y. Ban, L. Girin, X. Alameda-Pineda, and R. Horaud
    in IEEE Journal of Selected Topics in Signal Processing
    [ bib | pdf | arxiv ]
    @article{Li-JSTSP-2019,
      title={Online Localization and Tracking of Multiple Moving Speakers in Reverberant Environment},
      author={Xiaofei Li and Yutong Ban and Laurent Girin and Xavier Alameda-Pineda and Radu Horaud},
      journal={IEEE Journal of Selected Topics in Signal Processing},
      volumne=13,
      number=1,
      year={2019},
      pages={88--103},
      arxiv={https://arxiv.org/abs/1809.10936},
      doi={10.1109/JSTSP.2019.2903472},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Li-JSTSP-2019.pdf}
    }
  7. Increasing Image Memorability with Neural Style Transfer
    by A. Siarohin, G. Zen, C. Majtanovic, X. Alameda-Pineda, E. Ricci, and N. Sebe
    in ACM Transactions on Multimedia Computing Communications and Applications
    Award ACM TOMM Nicolas D. Georganas Award
    [ bib | pdf ]
    @article{Siarohin-TOMM-2019,
      title={Increasing Image Memorability with Neural Style Transfer},
      author={A Siarohin and G. Zen and C Majtanovic and X. Alameda-Pineda and E. Ricci and N. Sebe},
      journal={ACM Transactions on Multimedia Computing Communications and Applications},
      year={2019},
      doi={10.1145/3311781},
      award = {ACM TOMM Nicolas D. Georganas Award},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Siarohin-TOMM-2019.pdf}
    }

2018

  1. ACM MM’18 Workshop on Understanding Subjective Attributes of Data, Multimodal Recognition of Evoked Emotions
    by X. Alameda-Pineda, M. Redi, N. Sebe, S. Chang, and J. Luo
    in ACM International Conference on Multimedia
    [ bib | pdf ]
    @inproceedings{Alameda-EEUSAD-2018,
    author={Xavier Alameda-Pineda and Miriam Redi and Nicu Sebe and Shih-Fu Chang and Jiebo Luo},
    title={{ACM MM}'18 Workshop on Understanding Subjective Attributes of Data, Multimodal Recognition of Evoked Emotions},
    booktitle={ACM International Conference on Multimedia},
    address={Seoul, Korea},
    year=2018,
    doi={10.1145/3240508.3243721},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-EEUSAD-2018.pdf}
    }
  2. Accounting for Room Acoustics in Audio-Visual Multi-Speaker Tracking
    by Y. Ban, X. Li, X. Alameda-Pineda, L. Girin, and R. Horaud
    in IEEE International Conference on Audio, Speech and Signal Processing
    [ bib | pdf ]
    @inproceedings{Ban-ICASSP-2018,
    title={Accounting for Room Acoustics in Audio-Visual Multi-Speaker Tracking},
    author={Yutong Ban and Xiaofei Li and Xavier Alameda-Pineda and Laurent Girin and Radu Horaud},
    booktitle={IEEE International Conference on Audio, Speech and Signal Processing},
    doi={10.1109/ICASSP.2018.8462100},
    year={2018},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ban-ICASSP-2018.pdf}
    }
  3. DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model
    by S. Lathuilière, P. Mesejo, X. Alameda-Pineda, and R. Horaud
    in European Conference on Computer Vision
    [ bib | pdf ]
    @inproceedings{Lathuiliere-ECCV-2018,
      author={St\'ephane Lathuili\`ere and Pablo Mesejo and Xavier Alameda-Pineda and Radu Horaud},
      title={DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model},
      booktitle={European Conference on Computer Vision},
      address={Munich, Germany},
      year={2018},
      doi={10.1007/978-3-030-01228-1_13},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Lathuiliere-ECCV-2018.pdf}
    }
  4. A cascaded multiple-speaker localization and tracking system
    by X. Li, Y. Ban, L. Girin, X. Alameda-Pineda, and R. Horaud
    in International Workshop on Acoustic Signal Enhancement (IWAENC), LOCATA Satellite Workshop
    [ bib | pdf ]
    @inproceedings{Li-IWAENC-2018,
      author={X. Li and Y. Ban and L. Girin and X. Alameda-Pineda and R. Horaud},
      title={A cascaded multiple-speaker localization and tracking system},
      booktitle={International Workshop on Acoustic Signal Enhancement (IWAENC), LOCATA Satellite Workshop},
      year={2018},
      keywords={workshop},
      address={Tokyo, Japan},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Li-IWAENC-2018.pdf}
    }
  5. Every Smile is Unique: Landmark-Guided Diverse Smile Generation
    by W. Wei, X. Alameda-Pineda, D. Xu, E. Ricci, and N. Sebe
    in IEEE International Conference on Computer Vision and Pattern Recognition
    [ bib | pdf | arxiv ]
    @inproceedings{Wang-CVPR-2018,
      title={Every Smile is Unique: Landmark-Guided Diverse Smile Generation},
      author={Wei, Wang and Alameda-Pineda, Xavier and Xu, Dan and Ricci, Elisa and Sebe, Nicu},
      booktitle={IEEE International Conference on Computer Vision and Pattern Recognition},
      year={2018},
      arxiv={http://arxiv.org/abs/1802.01873/},
      address={Salt Lake City, USA},
      doi={10.1109/CVPR.2018.00740},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Wang-CVPR-2018.pdf}
    }
  6. Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval
    by D. Xu, X. Alameda-Pineda, J. Song, E. Ricci, and N. Sebe
    in IEEE Transactions on Image Processing
    [ bib | pdf | arxiv ]
    @article{Xu-TIP-2018,
      title={Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval},
      author={Dan Xu and Xavier Alameda-Pineda and Jingkuan Song and Elisa Ricci and Nicu Sebe},
      journal={IEEE Transactions on Image Processing},
      year={2018},
      arxiv={https://arxiv.org/abs/1803.01504},
      doi={10.1109/TIP.2018.2837381},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-TIP-2018.pdf}
    }

2017

  1. Viraliency: Pooling local virality
    by X. Alameda-Pineda, A. Pilzer, D. Xu, N. Sebe, and E. Ricci
    in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
    [ bib | pdf ]
    @inproceedings{Alameda-CVPR-2017,
      title={Viraliency: Pooling local virality},
      author={Alameda-Pineda, Xavier and Pilzer, Andrea and Xu, Dan and Sebe, Nicu and Ricci, Elisa},
      booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
      pages={6080--6088},
      year={2017},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-CVPR-2017.pdf}
    }
  2. MUSA2 — First ACM Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes
    by X. Alameda-Pineda, M. Redi, M. Soleymani, N. Sebe, S. Chang, and S. Gosling
    in ACM Multimedia
    [ bib | pdf ]
    @inproceedings{Alameda-MUSA2-2017,
    author = {Xavier Alameda-Pineda and Miriam Redi and Mohammad Soleymani and Nicu Sebe and Shih-Fu Chang and Samuel Gosling},
    title = {MUSA2 -- First ACM Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes},
    booktitle = {ACM Multimedia},
    year = {2017},
    address = {Mountain View, USA},
    doi={10.1145/3123266.3132057},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-MUSA2-2017.pdf}
    }
  3. Exploiting the Complementarity of Audio-Visual Data for Probabilistic Multi-Speaker Tracking
    by Y. Ban, L. Girin, X. Alameda-Pineda, and R. Horaud
    in IEEE ICCV Workshop on Computer Vision for Audio-Visual Media
    [ bib | pdf ]
    @inproceedings{Ban-CVAVM-2017,
    author = {Yutong Ban and Laurent Girin and Xavier Alameda-Pineda and Radu Horaud},
    title = {Exploiting the Complementarity of Audio-Visual Data for Probabilistic Multi-Speaker Tracking},
    booktitle = {IEEE ICCV Workshop on Computer Vision for Audio-Visual Media}, 
    year = {2017},
    keywords={workshop},
    doi={10.1109/ICCVW.2017.60},
    address = {Venice, Italy},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ban-CVAVM-2017.pdf}
    }
  4. Tracking a Varying Number of People with a Visually-Controlled Robotic Head
    by Y. Ban, X. Alameda-Pineda, F. Badeig, S. Ba, and R. Horaud
    in Intelligent Robots and Systems
    Award Novel Technology Paper Award Finalist
    [ bib | pdf ]
    @inproceedings{Ban-IROS-2017,
      title={Tracking a Varying Number of People with a Visually-Controlled Robotic Head},
      author={Yutong Ban and Xavier Alameda-Pineda and Fabien Badeig and Sileye Ba and Radu Horaud},
      booktitle={Intelligent Robots and Systems},
      award={Novel Technology Paper Award Finalist},
      year={2017},
      doi={10.1109/IROS.2017.8206274},
      address={Vancouver,Canada},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ban-IROS-2017.pdf}
    }
  5. Automatic Animation of an Articulatory Tongue Model from Ultrasound Images of the Vocal Tract
    by D. Fabre, T. Hueber, L. Girin, X. Alameda-Pineda, and P. Badin
    in Speech Communications
    [ bib | pdf ]
    @article{Fabre-SpeechCom-2017,
      title={Automatic Animation of an Articulatory Tongue Model from Ultrasound Images of the Vocal Tract},
      author={Diandra Fabre and Thomas Hueber and Laurent Girin and Xavier Alameda-Pineda and Pierre Badin},
      journal={Speech Communications},
      year={2017},
      volume={93},
      pages={63--75},
      doi={10.1016/j.specom.2017.08.002},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Fabre-SpeechCom-2017.pdf}
    }
  6. Adaptation of a Gaussian Mixture Regressor to a New Input Distribution: Extending the C-GMR Framework
    by L. Girin, T. Hueber, and X. Alameda-Pineda
    in International Conference on Latent Variable Analysis and Signal Separation
    [ bib | pdf ]
    @inproceedings{Girin-LVA-2017,
      title={Adaptation of a {G}aussian Mixture Regressor to a New Input Distribution: Extending the {C-GMR} Framework},
      author={Laurent Girin and Thomas Hueber and Xavier Alameda-Pineda},
      year={2017},
      booktitle={International Conference on Latent Variable Analysis and Signal Separation},
      address={Grenoble, France},
      doi={10.1007/978-3-319-53547-0_43},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Girin-LVA-2017.pdf}
    }
  7. Extending the Cascaded Gaussian Mixture Regression Framework for Cross-Speaker Acoustic-Articulatory Mapping
    by L. Girin, T. Hueber, and X. Alameda-Pineda
    in IEEE/ACM Transactions on Audio, Speech, and Language Processing
    [ bib | pdf ]
    @article{Girin-TASLP-2017,
      author={L. Girin and T. Hueber and X. Alameda-Pineda},
      journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
      title={Extending the Cascaded Gaussian Mixture Regression Framework for Cross-Speaker Acoustic-Articulatory Mapping},
      year={2017},
      doi={10.1109/TASLP.2017.2651398},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Girin-TASLP-2017.pdf}
    }
  8. Exploting the Intermittency of Speech for Joint Separation and Diarization
    by D. Kounades-Bastian, L. Girin, X. Alameda-Pineda, R. Horaud, and S. Gannot
    in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
    [ bib | pdf ]
    @inproceedings{Kounades-WASPAA-2017,
    author = {Dionyssos Kounades-Bastian and Laurent Girin and Xavier Alameda-Pineda and Radu Horaud and Sharon Gannot},
    title = {Exploting the Intermittency of Speech for Joint Separation and Diarization},
    booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics},
    year = {2017},
    doi={10.1109/WASPAA.2017.8169991},
    address = {New Paltz, USA},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Kounades-WASPAA-2017.pdf}
    }
  9. How to Make an Image More Memorable? A Deep Style Transfer Approach
    by A. Siarohin, G. Zen, C. Majtanovic, X. Alameda-Pineda, E. Ricci, and N. Sebe
    in ACM International Conference on Multimedia Retrieval
    [ bib | pdf ]
    @inproceedings{Siarohin-ICMR-2017,
      author = {Aliaksandr Siarohin and Gloria Zen and Cveta Majtanovic and Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe},
      title = {How to Make an Image More Memorable? A Deep Style Transfer Approach},
      booktitle = {ACM International Conference on Multimedia Retrieval},
      year = {2017},
      doi={10.1145/3078971.3078986},
      address = {Bucharest, Romania},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Siarohin-ICMR-2017.pdf}
    }
  10. Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
    by D. Xu, W. Ouyang, X. Alameda-Pineda, E. Ricci, X. Wang, and N. Sebe
    in Advances in Neural Information Processing Systems
    [ bib | pdf ]
    @inproceedings{Xu-NIPS-2017,
      title={Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction},
      author={Dan Xu and Wanli Ouyang and Xavier Alameda-Pineda and Elisa Ricci and Xiaogang Wang and Nicu Sebe},
      booktitle={Advances in Neural Information Processing Systems},
      year={2017},
      address={Long Beach, USA},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-NIPS-2017.pdf}
    }
  11. An EM algorithm for joint source separation and diarisation of multichannel convolutive mixtures
    by D. Kounades-Bastian, L. Girin, X. Alameda-Pineda, S. Gannot, and R. Horaud
    in IEEE International Conference on Audio, Speech and Signal Processing
    [ bib | pdf ]
    @inproceedings{Kounades-ICASSP-2017,
    title={An {EM} algorithm for joint source separation and diarisation of multichannel convolutive mixtures},
    author={Dionyssos Kounades-Bastian and Laurent Girin and Xavier Alameda-Pineda and Sharon Gannot and Radu Horaud},
    doi={10.1109/ICASSP.2017.7951789},
    booktitle={IEEE International Conference on Audio, Speech and Signal Processing},
    year={2017},
    address={New Orleans, USA},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Kounades-ICASSP-2017.pdf}
    }

2016

  1. Recognizing Emotions from Abstract Paintings using Non-Linear Matrix Completion
    by X. Alameda-Pineda, E. Ricci, Y. Yan, and N. Sebe
    in IEEE International Conference on Computer Vision and Pattern Recognition
    [ bib | pdf ]
    @inproceedings{Alameda-CVPR-2016,
      author = {Xavier Alameda-Pineda and Elisa Ricci and Yan Yan and Nicu Sebe},
      title = {Recognizing Emotions from Abstract Paintings using Non-Linear Matrix Completion},
      booktitle = {IEEE International Conference on Computer Vision and Pattern Recognition},
      year = {2016},
      doi={10.1109/CVPR.2016.566},
      soft = {https://github.com/xavirema/nlmc},
      address = {Las Vegas, USA},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-CVPR-2016.pdf}
    }
  2. SALSA: A Novel Dataset for Multimodal Group Behavior Analysis
    by X. Alameda-Pineda, J. Staiano, R. Subramanian, L. M. Batrinca, E. Ricci, B. Lepri, O. Lanz, and N. Sebe
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf | data | arxiv ]
    @article{Alameda-TPAMI-2016,
      author    = {Xavier Alameda-Pineda and
                   Jacopo Staiano and
                   Ramanathan Subramanian and
                   Ligia Maria Batrinca and
                   Elisa Ricci and
                   Bruno Lepri and
                   Oswald Lanz and
                   Nicu Sebe},
      title     = {{SALSA:} {A} Novel Dataset for Multimodal Group Behavior Analysis},
      journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
      year      = {2016},
      volume={38},
      number={8},
      pages={1707-1720},
      data    = {http://tev.fbk.eu/salsa},
      arxiv = {http://arxiv.org/abs/1506.06882},
      doi  = {10.1109/TPAMI.2015.2496269},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-TPAMI-2016.pdf}
    }
  3. An On-line Variational Bayesian Model for Multi-Person Tracking from Cluttered Scenes
    by S. Ba, X. Alameda-Pineda, A. Xompero, and R. Horaud
    in Computer Vision and Image Understanding
    [ bib | pdf | arxiv ]
    @article{Ba-CVIU-2016,
      title = {An On-line Variational Bayesian Model for Multi-Person Tracking from Cluttered Scenes},
      author = {Sileye Ba and Xavier Alameda-Pineda and Alessio Xompero and Radu Horaud},
      journal = {Computer Vision and Image Understanding},
      year={2016},
      volume = {153},
      number={},
      pages = {64-76},
      arxiv = {http://arxiv.org/abs/1509.01520},
      doi={10.1016/j.cviu.2016.07.006},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ba-CVIU-2016.pdf}
    }
  4. Tracking Multiple Persons Based on a Variational Bayesian Model
    by Y. Ban, S. Ba, X. Alameda-Pineda, and R. Horaud
    in European Conference on Computer Vision Workshops
    [ bib | pdf ]
    @inproceedings{Ban-ECCVW-2016,
      title={Tracking Multiple Persons Based on a Variational Bayesian Model},
      author={Ban, Yutong and Ba, Sileye and Alameda-Pineda, Xavier and Horaud, Radu},
      booktitle={European Conference on Computer Vision Workshops},
      pages={52--67},
      address={Amsterdam},
      keywords={workshop},
      year={2016},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Ban-ECCVW-2016.pdf}
    }
  5. EM algorithms for weighted-data clustering with application to audio-visual scene analysis
    by I. Gebru, X. Alameda-Pineda, F. Forbes, and R. Horaud
    in IEEE Transactions on Pattern Analysis and Machine Intelligence
    [ bib | pdf | data | arxiv ]
    @article{Gebru-TPAMI-2016,
       title = {{EM} algorithms for weighted-data clustering with application to audio-visual scene analysis},
       author = {Israel-Dejene Gebru and Xavier Alameda-Pineda and Florence Forbes and Radu Horaud},
       journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
       year={2016},
       volume={38},
       number={12},
       pages={2402-2415},
       arxiv = {http://arxiv.org/abs/1509.01509},
       doi={10.1109/TPAMI.2016.2522425},
       soft={http://perception.inrialpes.fr/people/Gebru/code/WD-EM.zip},
       data={https://team.inria.fr/perception/avtrack1/},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Gebru-TPAMI-2016.pdf}
    }
  6. An inverse-gama source variance prior with factorized parametrization for audio source separation
    by D. Kounades-Bastian, L. Girin, X. Alameda-Pineda, S. Gannot, and R. Horaud
    in IEEE International Conference on Audio, Speech and Signal Processing
    [ bib | pdf ]
    @inproceedings{Kounades-ICASSP-2016,
      TITLE = {An inverse-gama source variance prior with factorized parametrization for audio source separation},
      AUTHOR = {Kounades-Bastian, Dionyssos and Girin, Laurent and Alameda-Pineda, Xavier and Gannot, Sharon and Horaud, Radu},
      BOOKTITLE = {IEEE International Conference on Audio, Speech and Signal Processing},
      YEAR = {2016},
      address = {Shangai, China},
      pages={136-140},
      doi={10.1109/ICASSP.2016.7471652},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Kounades-ICASSP-2016.pdf}
    }
  7. A Variational EM Algorithm for the Separation of Time-Varying Convolutive Audio Mixtures
    by D. Kounades-Bastian, L. Girin, X. Alameda-Pineda, S. Gannot, and R. Horaud
    in IEEE/ACM Transactions on Audio, Speech and Language Processing
    [ bib | pdf | arxiv ]
    @article{Kounades-TASLP-2016,
      title={A Variational {EM} Algorithm for the Separation of Time-Varying Convolutive Audio Mixtures},
      author = {Dionyssos Kounades-Bastian and Laurent Girin and Xavier Alameda-Pineda and Sharon Gannot and Radu Horaud},
      journal = {IEEE/ACM Transactions on Audio, Speech and Language Processing},
      year = {2016},
      arxiv = {http://arxiv.org/abs/1510.04595},
      volume={24},
      number={8},
      pages={1408-1423},
      doi={10.1109/TASLP.2016.2554286},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Kounades-TASLP-2016.pdf}
    }
  8. Self-Adaptive Matrix Completion for Heart Rate Estimation from Face Videos under Realistic Conditions
    by S. Tulyakov, X. Alameda-Pineda, E. Ricci, L. Yin, J. F. Cohn, and N. Sebe
    in IEEE International Conference on Computer Vision and Pattern Recognition
    [ bib | pdf ]
    @inproceedings{Tulyakov-CVPR-2016,
        author = {Sergey Tulyakov and Xavier Alameda-Pineda and Elisa Ricci and Lijun Yin and Jeffrey F. Cohn and Nicu Sebe},
        title = {Self-Adaptive Matrix Completion for Heart Rate Estimation from Face Videos under Realistic Conditions},
        booktitle = {IEEE International Conference on Computer Vision and Pattern Recognition},
        doi={10.1109/CVPR.2016.263},
        year = {2016},
        address = {Las Vegas, USA},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Tulyakov-CVPR-2016.pdf}
    }
  9. Projective Unsupervised Flexible Embedding with Optimal Graph
    by W. Wang, Y. Yan, F. Nie, X. Alameda-Pineda, S. Yan, and N. Sebe
    in British Machine Vision Conference
    [ bib | pdf ]
    @inproceedings{Wang-BMVC-2016,
    title = {Projective Unsupervised Flexible Embedding with Optimal Graph},
    author = {Wei Wang and Yan Yan and Feiping Nie and Xavier Alameda-Pineda and Shuicheng Yan and Nicu Sebe},
    booktitle = {British Machine Vision Conference},
    year = 2016,
    address = {York, United Kingdom},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Wang-BMVC-2016.pdf}
    }
  10. Academic Coupled Dictionary Learning for Sketch-based Image Retrieval
    by D. Xu, X. Alameda-Pineda, J. Song, E. Ricci, and N. Sebe
    in ACM International Conference on Multimedia
    [ bib | pdf ]
    @inproceedings{Xu-ACMMM-2016,
        title={Academic Coupled Dictionary Learning for Sketch-based Image Retrieval},
        author={Dan Xu and Xavier Alameda-Pineda and Jingkuan Song and Elisa Ricci and Nicu Sebe},
        booktitle={ACM International Conference on Multimedia},
        year={2016},
        doi={10.1145/2964284.2964329},
        address={Amsterdam, The Netherlands},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-ACMMM-2016.pdf}
    }
  11. Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition
    by D. Xu, J. Song, X. Alameda-Pineda, E. Ricci, and N. Sebe
    in IEEE International Conference on Pattern Recognition
    Award Best Intel Scientific Award
    [ bib | pdf ]
    @inproceedings{Xu-ICPR-2016,
        title={Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition},
        author={Dan Xu and Jingkuan Song and Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe},
        booktitle={IEEE International Conference on Pattern Recognition},
        year={2016},
        doi={10.1109/ICPR.2016.7900132},
        address={Cancun, Mexico},
        award={Best Intel Scientific Award},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Xu-ICPR-2016.pdf}
    }

2015

  1. Vision-Guided Robot Hearing
    by X. Alameda-Pineda and R. Horaud
    in International Journal of Robotics Research
    [ bib | pdf | arxiv ]
    @article{Alameda-IJRR-2014,
      author    = {Xavier Alameda-Pineda and Radu Horaud},
      title     = {Vision-Guided Robot Hearing},
      journal   = {{International Journal of Robotics Research}},
      volume  = {34},
      number  = {4-5},
      pages    = {437--456},
      year    = {2015},
      arxiv = {http://arxiv.org/abs/1311.2460},
      soft = {https://code.humavips.eu},
      doi={10.1177/0278364914548050},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-IJRR-2014.pdf}
    }
  2. Analyzing Free-standing Conversational Groups: A Multimodal Approach
    by X. Alameda-Pineda, Y. Yan, E. Ricci, O. Lanz, and N. Sebe
    in ACM International Conference on Multimedia
    Award Best Paper Award
    [ bib | pdf ]
    @inproceedings{Alameda-ACMMM-2015,
      author = {Xavier Alameda-Pineda and Yan Yan and Elisa Ricci and Oswald Lanz and Nicu Sebe},
      title = {Analyzing Free-standing Conversational Groups: A Multimodal Approach}, 
      booktitle = {ACM International Conference on Multimedia},
      year = {2015},
      award = {Best Paper Award},
      pages = {4--15},
      address = {Brisbane, Australia},
      doi={10.1145/2733373.2806238},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-ACMMM-2015.pdf}
    }
  3. Speaker-Adaptive Acoustic-Articulatory Inversion using Cascaded Gaussian Mixture Regression
    by T. Hueber, L. Girin, X. Alameda-Pineda, and G. Bailly
    in IEEE/ACM Transactions on Audio, Speech and Language Processing
    [ bib | pdf ]
    @article{Hueber-TASLP-2015,
      title={Speaker-Adaptive Acoustic-Articulatory Inversion using Cascaded Gaussian Mixture Regression},
      author={Hueber, Thomas and Girin, Laurent and Alameda-Pineda, Xavier and Bailly, Gerard},
      year={2015},
      journal={IEEE/ACM Transactions on Audio, Speech and Language Processing},
      volume={23},
      number={12},
      pages={2246-2259},
      doi={10.1109/TASLP.2015.2464702},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Hueber-TASLP-2015.pdf}
    }
  4. A Variational EM Algorithm for the Separation of Moving Sound Sources
    by D. Kounades-Bastian, L. Girin, X. Alameda-Pineda, S. Gannot, and R. Horaud
    in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
    Award Best Student Paper Award
    [ bib | pdf ]
    @inproceedings{Kounades-WASPAA-2015,
      TITLE = {{A Variational EM Algorithm for the Separation of Moving Sound Sources}},
      AUTHOR = {Kounades-Bastian, Dionyssos and Girin, Laurent and Alameda-Pineda, Xavier and Gannot, Sharon and Horaud, Radu},
      BOOKTITLE = {{IEEE Workshop on Applications of Signal Processing to Audio and Acoustics}},
      YEAR = {2015},
      award={Best Student Paper Award},
      pages = {1--5},
      address = {New Paltz, USA},
      doi={10.1109/WASPAA.2015.7336936},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Kounades-WASPAA-2015.pdf}
    }

2014

  1. A Geometric Approach to Sound Source Localization from Time-Delay Estimates
    by X. Alameda-Pineda and R. Horaud
    in IEEE Transactions on Audio, Speech and Language Processing
    [ bib | pdf | arxiv ]
    @article{Alameda-TASLP-2014,
      author    = {Xavier Alameda-Pineda and Radu Horaud},
      title     = {A Geometric Approach to Sound Source Localization from Time-Delay Estimates},
      journal   = {{IEEE Transactions on Audio, Speech and Language Processing}},
      year      = {2014},
      volume   = {22}, 
      number   = {6}, 
      pages   = {1082-1095},
      arxiv = {http://arxiv.org/abs/1311.1047},
      soft = {https://team.inria.fr/perception/the-gtde-matlab-toolbox/},
      doi={10.1109/TASLP.2014.2317989},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-TASLP-2014.pdf}
    }
  2. Audio-Visual Speaker Localization via Weighted Clustering
    by I. Gebru, X. Alameda-Pineda, R. Horaud, and F. Forbes
    in IEEE Workshop on Machine Learning for Signal Processing
    [ bib | pdf ]
    @inproceedings{Gebru-MLSP-2014,
        title = {{Audio-Visual Speaker Localization via Weighted Clustering}},
        author = {Gebru, Israel-Dejene and Alameda-Pineda, Xavier and Horaud, Radu and Forbes, Florence},
        booktitle = {{IEEE Workshop on Machine Learning for Signal Processing}},
        year = {2014},
        pages = {1--6},
        address = {Reims, France},
        doi={10.1109/MLSP.2014.6958874},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Gebru-MLSP-2014.pdf}
    }
  3. Sound Representation and Classification Benchmark for Domestic Robots
    by M. Janvier, X. Alameda-Pineda, L. Girin, and R. Horaud
    in IEEE International Conference on Robotics and Automation
    [ bib | pdf | arxiv ]
    @inproceedings{Janvier-ICRA-2014,
      AUTHOR = {Janvier, Maxime and Alameda-Pineda, Xavier and Girin, Laurent and Horaud, Radu},
      TITLE = {{Sound Representation and Classification Benchmark for Domestic Robots}},
      BOOKTITLE = {{IEEE International Conference on Robotics and Automation}},
      YEAR = {2014},
      pages = {6285--6292},
      address = {Hong Kong, China},
      doi={10.1109/ICRA.2014.6907786},
      arxiv = {http://arxiv.org/abs/1402.3689},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Janvier-ICRA-2014.pdf}
    }

2013

  1. Benchmarking Methods for Audio-Visual Recognition Using Tiny Training Sets
    by X. Alameda-Pineda, J. Sanchez-Riera, and R. Horaud
    in IEEE International Conference on Acoustics, Speech, and Signal Processing
    [ bib | pdf ]
    @Inproceedings{Alameda-ICASSP-2013,
      author       = "Alameda-Pineda, Xavier and Sanchez-Riera, Jordi and Horaud, Radu",
      title        = "Benchmarking  Methods for Audio-Visual Recognition Using Tiny Training Sets",
      booktitle    = "IEEE International Conference on Acoustics, Speech, and Signal Processing",
      year         = "2013",
      pages = {3662--3666},
      address = {Vancouver, Canada},
      doi={10.1109/ICASSP.2013.6638341},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-ICASSP-2013.pdf}
    }
  2. RAVEL: An Annotated Corpus for Training Robots with Audiovisual Abilities
    by X. Alameda-Pineda, J. Sanchez-Riera, J. Wienke, V. Franc, J. Cech, K. Kulkarni, A. Deleforge, and R. Horaud
    in Journal on Multimodal User Interfaces
    [ bib | pdf | data ]
    @Article{Alameda-JMUI-2012,
      author       = "Alameda-Pineda, Xavier and Sanchez-Riera, Jordi and Wienke, Johannes and Franc, Vojtech and Cech, Jan and Kulkarni, Kaustubh and Deleforge, Antoine and Horaud, Radu",
      title        = "RAVEL: An Annotated Corpus for Training Robots with Audiovisual Abilities",
      journal      = "Journal on Multimodal User Interfaces",
      volume       = "7",
      number       = "1-2",
      pages        = "79-91",
      year         = "2013",
      data         = "http://ravel.humavips.eu",
      doi = {10.1007/s12193-012-0111-y},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-JMUI-2012.pdf}
    }
  3. The Geometry of Sound Source Localization Using Non-Coplanar Microphone Arrays
    by X. Alameda-Pineda, R. Horaud, and B. Mourrain
    in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
    [ bib | pdf ]
    @inproceedings{Alameda-WASPAA-2013,
      author = {Xavier Alameda-Pineda and Radu Horaud and Bernard Mourrain},
      title = {The Geometry of Sound Source Localization Using Non-Coplanar Microphone Arrays},
      booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics},
      year = {2013},
      pages = {1--4},
      address = {New Paltz, USA},
      soft = {https://team.inria.fr/perception/the-gtde-matlab-toolbox/},
      doi={10.1109/WASPAA.2013.6701849},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-WASPAA-2013.pdf}
    }
  4. Active-Speaker Detection and Localization with Microphones and Cameras Embedded into a Robotic Head
    by J. Cech, R. Mittal, A. Deleforge, J. Sanchez-Riera, X. Alameda-Pineda, and R. Horaud
    in IEEE-RAS International Conference on Humanoid Robots
    [ bib | pdf ]
    @inproceedings{Cech-Humanoids-2013, 
      author = {Cech, Jan and Mittal, Ravi and Deleforge, Antoine and Sanchez-Riera, Jordi and Alameda-Pineda, Xavier and Horaud, Radu}, 
      title = {{Active-Speaker Detection and Localization with Microphones and Cameras Embedded into a Robotic Head}}, 
      booktitle = {{IEEE-RAS International Conference on Humanoid Robots}},
      year = {2013},
      pages = {203--210},
      doi={10.1109/HUMANOIDS.2013.7029977},
      address = {Atlanta, USA},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Cech-Humanoids-2013.pdf}
    }

2012

  1. Geometrically-constrained Robust Time Delay Estimation Using Non-coplanar Microphone Arrays
    by X. Alameda-Pineda and R. Horaud
    in European Signal Processing Conference
    [ bib | pdf ]
    @InProceedings{Alameda-EUSIPCO-2012,
      author       = "Alameda-Pineda, Xavier and Horaud, Radu",
      title        = "Geometrically-constrained Robust Time Delay Estimation Using Non-coplanar Microphone Arrays",
      booktitle    = "European Signal Processing Conference",
      year         = "2012",
      pages = {1309--1313},
      address = {Bucarest, Romania},
      soft = {https://team.inria.fr/perception/the-gtde-matlab-toolbox/},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-EUSIPCO-2012.pdf}
    }
  2. Sound-Event Recognition with a Companion Humanoid
    by M. Janvier, X. Alameda-Pineda, L. Girin, and R. Horaud
    in IEEE-RAS International Conference on Humanoid Robotics
    [ bib | pdf ]
    @InProceedings{Janvier-Humanoids-2012,
      author       = "Janvier, Maxime and Alameda-Pineda, Xavier and Girin, Laurent and Horaud, Radu",
      title        = "Sound-Event Recognition with a Companion Humanoid",
      booktitle    = "IEEE-RAS International Conference on Humanoid Robotics",
      year         = "2012",
      pages = {104--111},
      address = {Osaka, Japan},
      doi={10.1109/HUMANOIDS.2012.6651506},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Janvier-Humanoids-2012.pdf}
    }
  3. Online Multimodal Speaker Detection for Humanoid Robots
    by J. Sanchez-Riera, X. Alameda-Pineda, J. Wienke, A. Deleforge, S. Arias, J. Cech, S. Wrede, and R. Horaud
    in IEEE-RAS International Conference on Humanoid Robotics
    [ bib | pdf ]
    @InProceedings{Sanchez-Humanoids-2012,
      author       = "Sanchez-Riera, Jordi and Alameda-Pineda, Xavier and Wienke, Johannes and Deleforge, Antoine and Arias, Soraya and Cech, Jan and Wrede, Sebastian and Horaud, Radu",
      title        = "Online Multimodal Speaker Detection for Humanoid Robots",
      booktitle    = "IEEE-RAS International Conference on Humanoid Robotics",
      year         = "2012",
      soft         = "http://code.humavips.eu",
      address = {Osaka, Japan},
      pages = {126--133},
      doi={10.1109/HUMANOIDS.2012.6651509},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sanchez-Humanoids-2012.pdf}
    }
  4. Audio-Visual Robot Command Recognition
    by J. Sanchez-Riera, X. Alameda-Pineda, and R. Horaud
    in IEEE/ACM International Conference on Multimodal Interaction
    [ bib | pdf ]
    @InProceedings{Sanchez-ICMI-2012,
      author       = "Sanchez-Riera, Jordi and Alameda-Pineda, Xavier and Horaud, Radu",
      title        = "Audio-Visual Robot Command Recognition",
      booktitle    = "IEEE/ACM International Conference on Multimodal Interaction",
      year         = "2012",
      address = {Santa Monica, USA},
      pages = {371--378},
      doi={10.1145/2388676.2388760},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sanchez-ICMI-2012.pdf}
    }

2011

  1. Finding Audio-Visual Events in Informal Social Gatherings
    by X. Alameda-Pineda, V. Khalidov, R. Horaud, and F. Forbes
    in IEEE/ACM International Conference on Multimodal Interfaces
    Award Oustanding Paper Award
    [ bib | pdf ]
    @InProceedings{Alameda-ICMI-2011,
      author       = "Alameda-Pineda, Xavier and Khalidov, Vasil and Horaud, Radu and Forbes, Florence",
      title        = "Finding Audio-Visual Events in Informal Social Gatherings",
      booktitle    = "IEEE/ACM International Conference on Multimodal Interfaces",
      year         = "2011",
      award         = "Oustanding Paper Award",
      pages = {247--254},
      address = {Alicante, Spain},
      doi={10.1145/2070481.2070527},
      soft = {https://code.humavips.eu},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-ICMI-2011.pdf}
    }

2008

  1. Image Compression with Generalized Lifting and partial knowledge of the signal PDF
    by J. C. Rolon, P. Salembier, and X. Alameda-Pineda
    in IEEE International Conference on Image Processing
    [ bib | pdf ]
    @InProceedings{Rolon-ICIP-2008,
      author       = "Rolon, Julio C. and Salembier, Philippe and Alameda-Pineda, Xavier",
      title        = "Image Compression with Generalized Lifting and partial knowledge of the signal PDF",
      booktitle    = "IEEE International Conference on Image Processing",
      year         = "2008",
      pages = {129--132},
      address = {San Diego, USA},
      doi = {10.1109/ICIP.2008.4711708},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Rolon-ICIP-2008.pdf}
    }

Preprints, books, chapters and patents

Preprints

  1. A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation
    by L. Airale, D. Vaufreydaz, and X. Alameda-Pineda
    in
    [ bib | pdf | arxiv ]
    @unpublished{Airale-2024,
      title={A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation},
      author={Louis Airale and Dominique Vaufreydaz and Xavier Alameda-Pineda},
      year={2024},
      arxiv={https://arxiv.org/abs/2307.03270},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Airale-2024.pdf}
    }
  2. HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE
    by X. Bie, W. Guo, S. Leglaive, L. Girin, F. Moreno-Noguer, and X. Alameda-Pineda
    in
    [ bib | pdf | arxiv ]
    @unpublished{Bie-2022,
      title={{HiT-DVAE}: Human Motion Generation via Hierarchical Transformer Dynamical {VAE}},
      author={Xiaoyu Bie and Wen Guo and Simon Leglaive and Lauren Girin and Francesc Moreno-Noguer and Xavier Alameda-Pineda},
      year={2022},
      arxiv={https://arxiv.org/abs/2204.01565},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Bie-2022.pdf}
    }
  3. VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space
    by G. Fiche, S. Leglaive, X. Alameda-Pineda, A. Agudo, and F. Moreno-Noguer
    in
    [ bib | pdf | arxiv ]
    @unpublished{Fiche-2024,
      title={{VQ-HPS}: Human Pose and Shape Estimation in a Vector-Quantized Latent Space},
      author={Gu\'enol\'e Fiche and Simon Leglaive and Xavier Alameda-Pineda and Antonio Agudo and Francesc Moreno-Noguer},
      year={2024},
      arxiv={https://arxiv.org/abs/2312.08291},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Fiche-2024.pdf}
    }
  4. GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling
    by Y. Liu, M. D. Nadai, J. Yao, N. Sebe, B. Lepri, and X. Alameda-Pineda
    in
    [ bib | pdf | arxiv ]
    @unpublished{Liu-2020,
    author={Yahui Liu and Marco De Nadai and Jian Yao and Nicu Sebe and Bruno Lepri and Xavier Alameda-Pineda},
    title={GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling},
    year={2020},
    arxiv={https://arxiv.org/abs/2003.06788},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Liu-2020.pdf}
    }
  5. Variational Structured Attention Networks for Deep Visual Representation Learning
    by G. Yang, P. Rota, X. Alameda-Pineda, D. Xu, M. Ding, and E. Ricci
    in
    [ bib | pdf | arxiv ]
    @unpublished{Yang-2021,
      title={Variational Structured Attention Networks for Deep Visual Representation Learning},
      author={Yang, Guanglei and Rota, Paolo and Alameda-Pineda, Xavier and Xu, Dan and Ding, Mingli and Ricci, Elisa},
      year={2021},
      arxiv={https://arxiv.org/abs/2103.03510},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Yang-2021.pdf}
    }

Books

  1. Multimodal Behavior Analysis in the Wild: Advances and Challenges
    by X. Alameda-Pineda, E. Ricci, N. Sebe, and others
    in
    [ bib | pdf ]
    @book{Alameda-Ricci-Sebe,
      author    = {Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe and others}, 
      editor    = {Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe}, 
      title     = {Multimodal Behavior Analysis in the Wild: Advances and Challenges},
      publisher = {Elsevier},
      year      = {2018},
      doi = {10.1016/C2017-0-01387-3},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-Ricci-Sebe.pdf}
    }

Book Chapters

  1. Multimodal analysis of free-standing conversational groups
    by X. Alameda-Pineda, E. Ricci, and N. Sebe
    in Frontiers of Multimedia Research
    [ bib | pdf ]
    @incollection{Alameda-BookMM-2017,
      author      = {Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe},
      title       = {Multimodal analysis of free-standing conversational groups},
      editor      = {Shih-Fu Chang},
      booktitle   = {Frontiers of Multimedia Research},
      doi        = {10.1145/3122865.3122869},
      publisher   = {Morgan and Claypool},
      year        = 2017,
      pages        = {51-74},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-BookMM-2017.pdf}
    }
  2. Multimodal behavior analysis in the wild: an introduction
    by X. Alameda-Pineda, E. Ricci, and N. Sebe
    in Multimodal behavior analysis in the wild
    [ bib | pdf ]
    @incollection{alameda2018multimodal-intro,
      author      = "Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe",
      title       = "Multimodal behavior analysis in the wild: an introduction",
      editor      = "Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe",
      booktitle   = "Multimodal behavior analysis in the wild",
      publisher   = "Elsevier",
      year        = 2018,
      pages       = "1-10",
      chapter     = 1,
      doi = {10.1016/B978-0-12-814601-9.00011-0},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-IntroBook-2018.pdf}
    }
  3. SALSA: A multimodal dataset for the automated analysis of free-standing social interactions
    by X. Alameda-Pineda, R. Subramanian, E. Ricci, O. Lanz, and N. Sebe
    in Group and Crowd Behavior for Computer Vision
    [ bib | pdf ]
    @incollection{Alameda-BookCBA-2016,
      author      = {Xavier Alameda-Pineda and Ramanathan Subramanian and Elisa Ricci and Oswald Lanz and Nicu Sebe},
      title       = {SALSA: A multimodal dataset for the automated analysis of free-standing social interactions},
      editor      = {Vittorio Murino and Marco Cristani and Shishir Shah and Silvio Savarese},
      booktitle   = {Group and Crowd Behavior for Computer Vision},
      year        = 2016,
      publisher   = {Elsevier},
      doi = {10.1016/B978-0-12-809276-7.00017-5},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Alameda-BookCBA-2016.pdf}
    }

Patents

  1. Self-adaptive matrix completion for heart rate estimation from face videos under realistic conditions
    by N. Sebe, X. Alameda-Pineda, S. Tulyakov, E. Ricci, L. Yin, and J. F. Cohn
    in
    [ bib | pdf ]
    @patent{Sebe-Patent-2017,
     author = {Nicu Sebe and Xavier Alameda-Pineda and Sergey Tulyakov and Elisa Ricci and Lijun Yin and Jeffrey F. Cohn},
     title = {Self-adaptive matrix completion for heart rate estimation from face videos under realistic conditions},
     year = {2017},
     number = {US 15631346},
     type = {Patent Application},
      pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Sebe-Patent-2017.pdf}
    }