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...
We propose a highly efficient framework for penalized likelihood kernel methods applied to multiclass models with a large, structured set of classes. As opposed to many previous a...
The emergence of data rich domains has led to an exponential growth in the size and number of data repositories, offering exciting opportunities to learn from the data using machin...
We describe an unsupervised system for learning narrative schemas, coherent sequences or sets of events (arrested(POLICE,SUSPECT), convicted( JUDGE, SUSPECT)) whose arguments are ...
We present a novel approach to recognizing Textual nt. Structural features are constructed from abstract tree descriptions, which are automatically extracted from syntactic depend...