-
Temporal Localization of Actions with Actoms
We address the problem of detecting actions, such as drinking or opening a door, in hours of challenging video data. We propose a model based on a sequence of atomic... -
Structured Models for Action Recognition in Real-word Videos
This dissertation introduces novel models to recognize broad action categories --- like "opening a door" and "running" --- in real-world video data such as movies and... -
Dense trajectories and motion boundary descriptors for action recognition
International audience -
Temporal Localization of Actions with Actoms
International audience -
Real time actions recognition from examplars
With the success of new interactive solution, like the Wii-Remote or the Sony Eyetoy, and more recently the Microsoft Kinect, we work on new interactions between game... -
Activity representation with motion hierarchies
International audience -
Audio-visual capabilities in humanoid robot NAO
In this thesis we plan to investigate the complementarity of auditory and visual sensory data for building a high-level interpretation of a scene. The audiovisual (AV)... -
Context based modeling for video semantic annotation
Recent years have witnessed an explosion of multimedia contents available. In 2010the video sharing website YouTube announced that 35 hours of videos were uploadedon... -
Enhanced image and video representation for visual recognition
The subject of this thesis is about image and video representations for visual recognition. This thesis first focuses on image search, both for image and textual...
