Stéphane Pateux
YOU?
Author Swipe
View article: 3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom
3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom Open
3D Gaussian Splatting (3DGS) is a major breakthrough in 3D scene reconstruction. With a number of views of a given object or scene, the algorithm trains a model composed of 3D gaussians, which enables the production of novel views from arb…
View article: Adam SLAM - the last mile of camera calibration with 3DGS
Adam SLAM - the last mile of camera calibration with 3DGS Open
The quality of the camera calibration is of major importance for evaluating progresses in novel view synthesis, as a 1-pixel error on the calibration has a significant impact on the reconstruction quality. While there is no ground truth fo…
View article: Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification Open
Transductive Few-Shot learning has gained increased attention nowadays considering the cost of data annotations along with the increased accuracy provided by unlabelled samples in the domain of few shot. Especially in Few-Shot Classificati…
View article: Easy—Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components
Easy—Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components Open
Few-shot classification aims at leveraging knowledge learned in a deep learning model, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have seen a f…
View article: Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning Open
In many real-life problems, it is difficult to acquire or label large amounts of data, resulting in so-called few-shot learning problems. However, few-shot classification is a challenging problem due to the uncertainty caused by using few …
View article: EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Open
Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have see…
View article: Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning Open
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed with the common aim of transferring knowledge acquired on a previously sol…
View article: Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning Open
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have …
View article: Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification Open
In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the info…
View article: Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning
Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning Open
This paper proposes a step toward obtaining general models of knowledge for facial analysis, by addressing the question of multi-source transfer learning. More precisely, the proposed approach consists in two successive training steps: the…
View article: Towards a General Model of Knowledge for Facial Analysis by Multi-Source\n Transfer Learning
Towards a General Model of Knowledge for Facial Analysis by Multi-Source\n Transfer Learning Open
This paper proposes a step toward obtaining general models of knowledge for\nfacial analysis, by addressing the question of multi-source transfer learning.\nMore precisely, the proposed approach consists in two successive training\nsteps: …
View article: MFAS: Multimodal Fusion Architecture Search
MFAS: Multimodal Fusion Architecture Search Open
We tackle the problem of finding good architectures for multimodal classification problems. We propose a novel and generic search space that spans a large number of possible fusion architectures. In order to find an optimal architecture fo…
View article: The Many Variations of Emotion
The Many Variations of Emotion Open
International audience
View article: Multi-Level Sensor Fusion with Deep Learning
Multi-Level Sensor Fusion with Deep Learning Open
In the context of deep learning, this article presents an original deep network, namely CentralNet, for the fusion of information coming from different sensors. This approach is designed to efficiently and automatically balance the trade-o…
View article: The Many Moods of Emotion
The Many Moods of Emotion Open
This paper presents a novel approach to the facial expression generation problem. Building upon the assumption of the psychological community that emotion is intrinsically continuous, we first design our own continuous emotion representati…
View article: Multilevel Sensor Fusion With Deep Learning
Multilevel Sensor Fusion With Deep Learning Open
In the context of deep learning, this article presents an original deep\nnetwork, namely CentralNet, for the fusion of information coming from different\nsensors. This approach is designed to efficiently and automatically balance the\ntrad…
View article: An Occam's Razor View on Learning Audiovisual Emotion Recognition with Small Training Sets
An Occam's Razor View on Learning Audiovisual Emotion Recognition with Small Training Sets Open
This paper presents a light-weight and accurate deep neural model for audiovisual emotion recognition. To design this model, the authors followed a philosophy of simplicity, drastically limiting the number of parameters to learn from the t…
View article: CAKE: Compact and Accurate K-dimensional representation of Emotion
CAKE: Compact and Accurate K-dimensional representation of Emotion Open
International audience
View article: CentralNet: a Multilayer Approach for Multimodal Fusion
CentralNet: a Multilayer Approach for Multimodal Fusion Open
This paper proposes a novel multimodal fusion approach, aiming to produce best possible decisions by integrating information coming from multiple media. While most of the past multimodal approaches either work by projecting the features of…
View article: Efficient Progressive Neural Architecture Search
Efficient Progressive Neural Architecture Search Open
This paper addresses the difficult problem of finding an optimal neural architecture design for a given image classification task. We propose a method that aggregates two main results of the previous state-of-the-art in neural architecture…
View article: CAKE: Compact and Accurate K-dimensional representation of Emotion
CAKE: Compact and Accurate K-dimensional representation of Emotion Open
Numerous models describing the human emotional states have been built by the psychology community. Alongside, Deep Neural Networks (DNN) are reaching excellent performances and are becoming interesting features extraction tools in many com…
View article: Temporal multimodal fusion for video emotion classification in the wild
Temporal multimodal fusion for video emotion classification in the wild Open
This paper addresses the question of emotion classification. The task consists in predicting emotion labels (taken among a set of possible labels) best describing the emotions contained in short video clips. Building on a standard framewor…
View article: Multi-Resolution Mesh-Based Motion Estimation Using A Backward In Forward Tracking Method
Multi-Resolution Mesh-Based Motion Estimation Using A Backward In Forward Tracking Method Open
Publication in the conference proceedings of EUSIPCO, Tampere, Finland, 2000
View article: Bit Rate And Local Quality Control Using A Rate/Distortion Criterion For On-Board Satellite Images Compression
Bit Rate And Local Quality Control Using A Rate/Distortion Criterion For On-Board Satellite Images Compression Open
Publication in the conference proceedings of EUSIPCO, Tampere, Finland, 2000