Weakly-supervised learning studies the problem of minimizing the amount of human effort required for training state-of-the-art models. This allows to leverage a large amount of data. However, in practice weakly-supervised methods perform significantly worse than their fully-supervised counterparts. This is also the case in deep learning, where the top-performing computer vision approaches remain fully-supervised, which limits their usage in real world applications. This thesis attempts to bridge the gap between weakly-supervised and fully-supervised methods by utilizing motion information. It also studies the problem of moving object segmentation itself, proposing one of the first learning-based methods for this task.We focus on the problem...
This thesis focuses on the problem of video salient object detection and video object instance segme...
Avec la récente et importante croissance des contenus vidéos, la compréhension automatique de vidéos...
Nowadays, the rapid increase of video creates a massive demand for video-based editing applications....
Weakly-supervised learning studies the problem of minimizing the amount of human effort required for...
L’apprentissage faiblement supervisé cherche à réduire au minimum l’effort humain requis pour entrai...
International audienceWe study the problem of segmenting moving objects in unconstrained videos. Giv...
With the recent overwhelming growth of digital video content, automatic video understanding has beco...
International audienceThe problem of determining whether an object is in motion, irrespective of cam...
The ability to recognize motion is one of the most important functions of our visual system. Motion ...
International audienceFully convolutional neural networks (FCNNs) trained on a large number of image...
International audienceThis paper addresses the task of segmenting moving objects in unconstrained vi...
To make artificial intelligence “see” the world is a primary step to making computers “learn”. Curre...
Computer vision plays a key role in Artificial Intelligence because of the rich semantic information...
Video object segmentation is gaining increased research and commercial importance in recent times fr...
This thesis focuses on the problem of video salient object detection and video object instance segme...
Avec la récente et importante croissance des contenus vidéos, la compréhension automatique de vidéos...
Nowadays, the rapid increase of video creates a massive demand for video-based editing applications....
Weakly-supervised learning studies the problem of minimizing the amount of human effort required for...
L’apprentissage faiblement supervisé cherche à réduire au minimum l’effort humain requis pour entrai...
International audienceWe study the problem of segmenting moving objects in unconstrained videos. Giv...
With the recent overwhelming growth of digital video content, automatic video understanding has beco...
International audienceThe problem of determining whether an object is in motion, irrespective of cam...
The ability to recognize motion is one of the most important functions of our visual system. Motion ...
International audienceFully convolutional neural networks (FCNNs) trained on a large number of image...
International audienceThis paper addresses the task of segmenting moving objects in unconstrained vi...
To make artificial intelligence “see” the world is a primary step to making computers “learn”. Curre...
Computer vision plays a key role in Artificial Intelligence because of the rich semantic information...
Video object segmentation is gaining increased research and commercial importance in recent times fr...
This thesis focuses on the problem of video salient object detection and video object instance segme...
Avec la récente et importante croissance des contenus vidéos, la compréhension automatique de vidéos...
Nowadays, the rapid increase of video creates a massive demand for video-based editing applications....