In this thesis, we focus on modeling interactions between people, objects and scenes and show benefits of combining corresponding cues for improving both action classification and scene understanding. In the first part, we seek to exploit the scene and object context to improve action classification in still images. We explore alternative bag-of-features models and propose a method that takes advantage of the scene context. We then propose a new model exploiting the object context for action classification based on pairs of body part and object detectors. We evaluate our methods on our newly collected still image dataset as well as three other datasets for action classification and show performance close to the state of the art. In the seco...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
In this thesis, we focus on modeling interactions between people, objects and scenes and show benefi...
In this thesis, we focus on modeling interactions between people, objects and scenes and show benefi...
Nous nous intéressons dans cette thèse à la modélisation des interactions entre personnes, objet...
With the massive increase of video content on Internet and beyond, the automatic understanding of vi...
This dissertation targets the recognition of human actions in realistic video data, such as movies. ...
International audienceWe investigate a discriminatively trained model of person-object interactions ...
This dissertation targets the recognition of human actions in realistic video data, such as movies. ...
International audienceOur everyday objects support various tasks and can be used by people for diffe...
This thesis targets recognition of human actions in videos. This problem can be defined as the abili...
This work addresses the problem of recognizing actions and interactions in realistic video settings ...
This work addresses the problem of recognizing actions and interactions in realistic video settings ...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
In this thesis, we focus on modeling interactions between people, objects and scenes and show benefi...
In this thesis, we focus on modeling interactions between people, objects and scenes and show benefi...
Nous nous intéressons dans cette thèse à la modélisation des interactions entre personnes, objet...
With the massive increase of video content on Internet and beyond, the automatic understanding of vi...
This dissertation targets the recognition of human actions in realistic video data, such as movies. ...
International audienceWe investigate a discriminatively trained model of person-object interactions ...
This dissertation targets the recognition of human actions in realistic video data, such as movies. ...
International audienceOur everyday objects support various tasks and can be used by people for diffe...
This thesis targets recognition of human actions in videos. This problem can be defined as the abili...
This work addresses the problem of recognizing actions and interactions in realistic video settings ...
This work addresses the problem of recognizing actions and interactions in realistic video settings ...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...
With the rapid growth of digital video content, automaticvideo understanding has become an increasin...