This paper exploits the context of natural dynamic scenes
for human action recognition in video. Human actions
are frequently constrained by the purpose and the physical
propert...
Marcin Marszalek (INRIA), Ivan Laptev (INRIA), Cor...
An automatic human shape-motion analysis method based on a fusion architecture is proposed for human action recognition in videos. Robust shape-motion features are extracted from h...
In soccer videos, most significant actions are usually followed by close–up shots of players that take part in the action itself. Automatically annotating the identity of the p...
The interpretation by a human of a scene in video material is heavily influenced by the context of the scene. As a result, researchers have recently made more use of context in th...
Ilias Kolonias, William J. Christmas, Josef Kittle...
Abstract. In [1], we presented a method for automatic detection of action items from natural conversation. This method relies on supervised classification techniques that are trai...