Data shared throughout the world has a major impact on the lives of billions of people. It is critical to be able to analyse this data automatically in order to measure and alter its impact. This analysis is tackled by training deep neural networks, which have reached competitive results in many domains. In this work, we focus on the understanding of daily life images, in particular on the interactions between objects and people that are visible in images, which we call visual relations.To complete this task, neural networks are trained in a supervised manner. This involves minimizing an objective function that quantifies how detected relations differ from annotated ones. Performance of these models thus depends on how widely and accurately...
The increasing interest in social networks, smart cities, and Industry 4.0 is encouraging the develo...
La récente mise à disposition de grandes bases de données de modèles 3D permet de nouvelles possibil...
This paper shows how a standard convolutional neural network (CNN) without recurrent connections is ...
Data shared throughout the world has a major impact on the lives of billions of people. It is critic...
Les données échangées en ligne ont un impact majeur sur les vies de milliards de personnes et il est...
International audienceA thorough comprehension of image content demands a complex grasp of the inter...
With the recent successes of deep learning and the growing interactions between humans and AIs, expl...
Co-localisées avec la Plate-Forme Intelligence Artificielle (PFIA 2019)International audienceDespite...
The goal of this thesis is the exploration of interactive object segmentation by applying convolutio...
In this thesis, we study the problem of detection of visual relations of the form (subject, predicat...
Nous étudions le problème de détection de relations visuelles de la forme (sujet, prédicat, objet) d...
Humans inevitably develop a sense of the relationships be-tween objects, some of which are based on ...
International audienceThis paper introduces a novel approach for modeling visual relations between p...
Humans and many animals can see the world and understand it effortlessly which gives some hope that ...
Les progrès récents des réseaux de neurones artificiels (plus connus sous le nom d'apprentissage pro...
The increasing interest in social networks, smart cities, and Industry 4.0 is encouraging the develo...
La récente mise à disposition de grandes bases de données de modèles 3D permet de nouvelles possibil...
This paper shows how a standard convolutional neural network (CNN) without recurrent connections is ...
Data shared throughout the world has a major impact on the lives of billions of people. It is critic...
Les données échangées en ligne ont un impact majeur sur les vies de milliards de personnes et il est...
International audienceA thorough comprehension of image content demands a complex grasp of the inter...
With the recent successes of deep learning and the growing interactions between humans and AIs, expl...
Co-localisées avec la Plate-Forme Intelligence Artificielle (PFIA 2019)International audienceDespite...
The goal of this thesis is the exploration of interactive object segmentation by applying convolutio...
In this thesis, we study the problem of detection of visual relations of the form (subject, predicat...
Nous étudions le problème de détection de relations visuelles de la forme (sujet, prédicat, objet) d...
Humans inevitably develop a sense of the relationships be-tween objects, some of which are based on ...
International audienceThis paper introduces a novel approach for modeling visual relations between p...
Humans and many animals can see the world and understand it effortlessly which gives some hope that ...
Les progrès récents des réseaux de neurones artificiels (plus connus sous le nom d'apprentissage pro...
The increasing interest in social networks, smart cities, and Industry 4.0 is encouraging the develo...
La récente mise à disposition de grandes bases de données de modèles 3D permet de nouvelles possibil...
This paper shows how a standard convolutional neural network (CNN) without recurrent connections is ...