by Xiaoyu Lin, Xiaoyu Bie, Simon Leglaive, Laurent Girin, and Xavier Alameda-Pineda IEEE International Conference on Acoustics, Speech and Signal Processing 2023 [paper][code] Abstract: The dynamical variational autoencoders (DVAEs) are a family of latent-variable deep generative models that extends the VAE to model a sequence of observed data and a…
by Wen Guo*, Yuming Du*, Xi Shen, Vincent Lepetit, Xavier Alameda-Pineda, and Francesc Moreno-Noguer IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023, Waikoloa, Hawaii [paper] [code] [HAL] Abstract. This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences. State-of-the-art…
by Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier SpeechCom, 2023 [arXiv] [HAL] [code] [examples] Abstract: Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of data. In speech processing, inspiring from the anatomical mechanisms…
by Anand Ballou, Xavier Alameda-Pineda, and Chris Reinke Applied Intelligence [paper][code] Abstract: With the increasing presence of robots in our everyday environments, improving their social skills is of utmost importance. Nonetheless, social robotics still faces many challenges. One bottleneck is that robotic behaviors often need to be adapted, as social…
by Chris Reinke and Xavier Alameda-Pineda Transactions on Machine Learning Research [Paper][Code] Abstract. Transfer in Reinforcement Learning aims to improve learning performance on target tasks using knowledge from experienced source tasks. Successor features (SF) are a prominent transfer mechanism in domains where the reward function changes between tasks. They reevaluate…
by Zhiqi Kang, Mostafa Sadeghi, Radu Horaud and Xavier Alameda-Pineda International Journal of Computer Vision, 2023, 131 (5), pp.1122-1140 [arXiv] [HAL] [webpage] Abstract. Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a frontalization methodology that preserves non-rigid facial deformations in order to boost…
By Guillaume Delorme*, Yihong Xu*, Luis G. Camara, Elisa Ricci, Radu Horaud, Xavier Alameda Pineda [arXiv] [paper] [code] Abstract: Existing works on multiple object tracking (MOT) are developed under the traditional supervised learning setting, where the training and test data are drawn from the same distribution. This hinders the development…
Guanglei Yang, Enrico Fini, Dan Xu, Paolo Rota, Mingli Ding, Hao Tang, Xavier Alameda-Pineda, Elisa Ricci IEEE Transactions on Multimedia [arXiv][HAL] Abstract. Over the past years, semantic segmentation, similar to many other tasks in computer vision, has benefited from the progress in deep neural networks, resulting in significantly improved performance. However, deep architectures trained…
Hanyu Xuan, Zhiliang Wu, Jian Yang, Yan Yan, Xavier Alameda-Pineda IEEE/CVF International Conference on Computer Vision (CVPR) 2022, New Orleans, US [HAL] Abstract. Humans can easily recognize where and how the sound is produced via watching a scene and listening to corresponding audio cues. To achieve such cross-modal perception on machines, existing methods…
by Enrico Fini, Victor G. Turrisi da Costa, Xavier Alameda-Pineda, Elisa Ricci, Karteek Alahari, Julien Mairal IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022, New Orleans, USA [arXiv][Code][HAL] Abstract. Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However,…
