List of Publications

@inproceedings{Sadok-ICASSP-2025,

title = {AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder},

author = {Samir Sadok and Simon Leglaive and Laurent Girin and Gaël Richard and Xavier Alameda-Pineda},

year  = {2025},

date = {2025-01-01},

booktitle = {IEEE International Conference on Audio, Speech, and Signal Processing},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Fiche-CVPR-2025,

title = {MEGA: Masked Generative Autoencoder for Human Mesh Recovery},

author = {Guénolé Fiche and Simon Leglaive and Xavier Alameda-Pineda and Francesc Moreno-Noguer},

year  = {2025},

date = {2025-01-01},

booktitle = {IEEE International Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ayilo-ICASSP-2025,

title = {Diffusion-based Unsupervised Audio-visual Speech Enhancement},

author = {Jean Eudes Ayilo and Mostafa Sadeghi and Romain Serizel and Xavier Alameda-Pineda},

year  = {2025},

date = {2025-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Audio Processing},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Vaquero-ECCV-2024,

title = {Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking},

author = {Lorenzo Vaquero and Yihong Xu and Xavier Alameda-Pineda and Victor M Brea and Manuel Mucientes},

doi = {10.1007/978-3-031-73464-9_27},

year  = {2024},

date = {2024-01-01},

booktitle = {European Conference on Computer Vision},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Pikuli-RSSW-2024,

title = {Navigating the Practical Pitfalls of Reinforcement Learning for Social Robot Navigation},

author = {Dhimiter Pikuli and Jordan Cosio and Xavier Alameda-Pineda and Pierre-Brice Wieber and Thierry Fraichard},

year  = {2024},

date = {2024-01-01},

booktitle = {Robotics: Science and Systems (RSS) Workshop on Unsolved Problems in Social Robot Navigation},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Fiche-ECCV-2024,

title = {VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space},

author = {Guénolé Fiche and Simon Leglaive and Xavier Alameda-Pineda and Antonio Agudo and Francesc Moreno-Noguer},

doi = {10.1007/978-3-031-72943-0_27},

year  = {2024},

date = {2024-01-01},

booktitle = {European Conference on Comptuer Vision},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.1109/ICASSP48485.2024.10446294},

year  = {2024},

date = {2024-01-01},

booktitle = {IEEE International Conference on Acoustics Speech and Signal Processing},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{DeMin-ICCVW-2023,

title = {On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers},

author = {Thomas De Min and Massimiliano Mancini and Karteek Alahari and Xavier Alameda-Pineda and Elisa Ricci},

year  = {2023},

date = {2023-01-01},

booktitle = {International Conference on Computer Vision Workshops},

keywords = {workshop},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.21437/Interspeech.2023-232},

year  = {2023},

date = {2023-01-01},

booktitle = {Interspeech},

pages = {5102-5106},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.1145/3623264.3624454},

year  = {2023},

date = {2023-01-01},

booktitle = {ACM SIGGRAPH Conference on Motion, Interaction and Games},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.1109/CVPR52729.2023.00311},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},

pages = {3187-3197},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.1109/ICASSP49357.2023.10096751},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Conference on Audio, Speech and Signal Processing},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Guo-WACV-2023,

title = {Back to MLP: A Simple Baseline for Human Motion Prediction},

author = {Wen Guo and Yuming Du and Xi Shen and Vincent Lepetit and Xavier Alameda-Pineda and Francesc Moreno-Noguer},

doi = {10.1109/WACV56688.2023.00479},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE Winter Conference on Applications of Computer Vision},

pages = {4809-4819},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.1145/3503161.3554769},

year  = {2022},

date = {2022-01-01},

booktitle = {ACM International Conference on Multimedia},

address = {Lisbon, Portugal},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Xuan-IJCAI-2022,

title = {Active Contrastive Set Mining for Robust Audio-Visual Instance Discrimination},

author = {Hanyu Xuan and Yihong Xu and Shuo Chen and Zhiliang Wu and Jian Yang and Yan Yan and Xavier Alameda-Pineda},

doi = {10.24963/ijcai.2022/506},

year  = {2022},

date = {2022-01-01},

booktitle = {International Joint Conference on Artificial Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Xuan-CVPR-2022,

title = {A Proposal-based Paradigm for Self-supervised Sound Source Localization in Videos},

author = {Hanyu Xuan and Zhiliang Wu and Jian Yang and Yan Yan and Xavier Alameda-Pineda},

doi = {10.1109/CVPR52688.2022.00110},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Fini-CVPR-2022,

title = {Self-supervised models are continual learners},

author = {Enrico Fini and Victor G Turrisi Costa and Xavier Alameda-Pineda and Elisa Ricci and Karteek Alahari and Julien Mairal},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},

pages = {9621–9630},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.21437/JEP.2022-69},

year  = {2022},

date = {2022-01-01},

booktitle = {XXXIVe Journées d'Études sur la Parole},

keywords = {french},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Guo-CVPR-2022,

title = {Multi-Person Extreme Motion Prediction with Cross-Interaction Attention},

author = {Wen Guo and Xiaoyu Bie and Xavier Alameda-Pineda and Francesc Moreno},

doi = {10.1109/CVPR52688.2022.01271},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Kang-ICASSP-2022,

title = {The impact of removing head movements on audio-visual speech enhancement},

author = {Zhiqi Kang and Mostafa Sadeghi and Radu Horaud and Xavier Alameda-Pineda and Jacob Donley and Anurag Kumar},

doi = {10.1109/ICASSP43922.2022.9746401},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},

pages = {7302–7306},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Sadeghi-ICASSP-2021,

title = {Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement},

author = {Mostafa Sadeghi and Xavier Alameda-Pineda},

doi = {10.1109/ICASSP39728.2021.9414097},

year  = {2021},

date = {2021-01-01},

booktitle = {IEEE International Conference on Audio, Speech and Signal Processing},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Nguyen-MLSP-2021,

title = {Deep Variational Generative Models for Audio-visual Speech Separation},

author = {Viet-Nhat Nguyen and Mostafa Sadeghi and Elisa Ricci and Xavier Alameda-Pineda},

doi = {10.1109/MLSP52302.2021.9596406},

year  = {2021},

date = {2021-01-01},

booktitle = {IEEE Workshop on Machine Learning for Signal Processing},

address = {Queensland, Australia},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

doi = {10.1109/WACV48630.2021.00284},

year  = {2021},

date = {2021-01-01},

booktitle = {IEEE Winter Conference on Applications of Computer Vision},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Emukpere-NeurIPSW-2021,

title = {Successor Feature Neural Episodic Control},

author = {David Emukpere and Xavier Alameda-Pineda and Chris Reinke},

year  = {2021},

date = {2021-01-01},

booktitle = {Fifth Workshop on Meta-Learning at the Conference on Neural Information Processing Systems},

keywords = {workshop},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Bie-Interspeech-2021,

title = {A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling},

author = {Xiaoyu Bie and Laurent Girin and Simon Leglaive and Thomas Hueber and Xavier Alameda-Pineda},

doi = {10.21437/Interspeech.2021-256},

year  = {2021},

date = {2021-01-01},

booktitle = {ISCA Interspeech},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Delorme-ICPR-2020,

title = {CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification},

author = {Guillaume Delorme and Yihong Xu and Stephane Lathuilière and Radu Horaud and Xavier Alameda-Pineda},

doi = {10.1109/ICPR48806.2021.9412431},

year  = {2020},

date = {2020-01-01},

booktitle = {IEEE International Conference on Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Sadeghi-ICASSP-2020,

title = {Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders},

author = {Mostafa Sadeghi and Xavier Alameda-Pineda},

doi = {10.1109/ICASSP40776.2020.9053730},

year  = {2020},

date = {2020-01-01},

booktitle = {IEEE International Conference on Audio, Speech and Signal Processing},

address = {Barcelona, Spain},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}