Learning Actions From the Web

14 years 9 months ago

Download cs-people.bu.edu

This paper proposes a generic method for action recognition in uncontrolled videos. The idea is to use images collected from the Web to learn representations of actions and use this knowledge to automatically annotate actions in videos. Our approach is unsupervised in the sense that it requires no human intervention other than the text querying. Its benefits are two-fold: 1) we can improve retrieval of action images, and 2) we can collect a large generic database of action poses, which can then be used in tagging videos. We present experimental evidence that using action images collected from the Web, annotating actions is possible.

Nazli Ikizler-Cinbis, R. Gokberk Cinbis, Stan Scla

Real-time Traffic

Computer Vision | Human Action Recognition | ICCV 2009 |

claim paper

» Selecting actions for resourcebounded information extraction using reinforcement learning

» Learning 3D Action Models from a few 2D videos for View Invariant Action Recognition

» Virtual Action Learning Experiences from a Study of an SME eLearning Programme

» Automatic Discovery of Action Taxonomies from Multiple Views

» Using Coordinated Atomic Actions for Building Complex Web Applications A Learning Experien...

» Constructing action set from basis functions for reinforcement learning of robot control

» Learning from actions not taken a multiagent learning algorithm

» Toward designing a robot that learns actions from parental demonstrations

Post Info
More Details (n/a)

Added	13 Jul 2009
Updated	10 Jan 2010
Type	Conference
Year	2009
Where	ICCV
Authors	Nazli Ikizler-Cinbis, R. Gokberk Cinbis, Stan Sclaroff

Comments (0)

Sciweavers

Learning Actions From the Web

Computer Vision | Human Action Recognition | ICCV 2009 |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers