Continual Attentive Fusion for Incremental Learning in Semantic Segmentation

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…

Continue reading

A Proposal-based Paradigm for Self-supervised Sound Source Localization in Videos

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…

Continue reading

Continual Models are Self-Supervised Learners

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,…

Continue reading

Multi Person Extreme Motion Prediction

by Wen Guo*, Xiaoyu Bie*, Xavier Alameda-Pineda and Francesc Moreno-Noguer IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022, New Orleans, USA [paper]  [code] [data] Abstract. Human motion prediction aims to forecast future poses given a sequence of past 3D skeletons. While this problem has recently received increasing attention, it has mostly been…

Continue reading

Successor Feature Neural Episodic Control

by Davier Emukpere, Xavier Alameda-Pineda and Chris Reinke [Paper] Abstract. A longstanding goal in reinforcement learning is to build intelligent agents that show fast learning and a flexible transfer of skills akin to humans and animals. This paper investigates the integration of two  frameworks for tackling those goals: episodic control and successor features. Episodic…

Continue reading

Dynamical Variational AutoEncoders

by Laurent Girin, Simon Leglaive, Xiaoyu Bie, Julien Diard, Thomas Hueber, and Xavier Alameda-Pineda Foundations and Trends in Machine Learning, 2021, Vol. 15, No. 1-2, pp 1–175. [Review paper] [Code] [Tutorial @ICASPP 2021] Abstract. Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional…

Continue reading

Performance Analysis of 3D Face Alignment with a Statistically Robust Confidence Test

by Mostafa Sadeghi,  Xavier Alameda-Pineda and Radu Horaud (submitted to IEEE Transactions on Image Processing) [Code & Data] Abstract: We address the problem of analyzing the performance of 3D face alignment (3DFA) algorithms. Traditionally, performance analysis relies on carefully annotated datasets. Here, these annotations correspond to the 3D coordinates of…

Continue reading

Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement

by Mostafa Sadeghi, Xavier Alameda-Pineda IEEE TSP, 2021 [paper] [arXiv] Abstract. In this paper, we are interested in unsupervised (unknown noise) speech enhancement, where the probability distribution of clean speech spectrogram is simulated via a latent variable generative model, also called the decoder. Recently, variational autoencoders (VAEs) have gained much popularity…

Continue reading

Seminar: Transfer Learning, Data Efficiency and Fairness in Deep Reinforcement Learning

Seminar by Matthieu Zimmer, UM-SJTU Monday, February 8th, 11:00 – 12:00 INRIA Montbonnot Saint-Martin   Abstract: In reinforcement learning, we aim at designing agents that take sequential decisions in unknown environments by learning through their own interaction with such environments. However, learning from scratch is often costly in terms of data to…

Continue reading

Variational Inference and Learning of Piecewise-linear Dynamical Systems

by Xavier Alameda-Pineda, Vincent Drouard, Radu Horaud IEEE TNNLS 2021 [PDF] [arXiv] Abstract Modeling the temporal behavior of data is of primordial importance in many scientific and engineering fields. Baseline methods assume that both the dynamic and observation equations follow linear-Gaussian  models. However, there are many real-world processes that cannot be characterized by…

Continue reading