Sciweavers

5082 search results - page 6 / 1017
» Actionable Information in Vision
Sort
View
ECCV
2010
Springer
14 years 15 days ago
Representing Pairwise Spatial and Temporal Relations for Action Recognition
The popular bag-of-words paradigm for action recognition tasks is based on building histograms of quantized features, typically at the cost of discarding all information about rela...
CVPR
2011
IEEE
13 years 3 months ago
Action Recognition from a Distributed Representation of Pose and Appearance
We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
Subhransu Maji, Lubomir Bourdev, Jitendra Malik
ISORC
2000
IEEE
13 years 12 months ago
A Vision of the Future for the Air Force (and Perhaps the Whole DoD)
The Air Force has enthusiastically endorsed, at its most senior levels, advanced thinking with regard to the application of information technology. Recently, the notion of a Joint...
Thomas F. Saunders
WAPCV
2007
Springer
14 years 1 months ago
Embodied Active Vision in Language Learning and Grounding
Abstract. Most cognitive studies of language acquisition in both natural systems and artificial systems have focused on the role of purely linguistic information as the central co...
Chen Yu
ACCV
2007
Springer
14 years 1 months ago
Viewpoint Insensitive Action Recognition Using Envelop Shape
Action recognition is a popular and important research topic in computer vision. However, it is challenging when facing viewpoint variance. So far, most researches in action recogn...
Feiyue Huang, Guangyou Xu