Sciweavers

185 search results - page 2 / 37
» Human action recognition using the motion of interest points
Sort
View
CVPR
2009
IEEE
15 years 13 days ago
Recognising Action as Clouds of Space-Time Interest Points
Much of recent action recognition research is based on space-time interest points extracted from video using a Bag of Words (BOW) representation. It mainly relies on the discrimi...
Matteo Bregonzio (Queen Mary, University of London...
CVPR
2010
IEEE
14 years 1 months ago
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Adriana Kovashka, Kristen Grauman
MM
2009
ACM
252views Multimedia» more  MM 2009»
13 years 12 months ago
Localizing volumetric motion for action recognition in realistic videos
This paper presents a novel motion localization approach for recognizing actions and events in real videos. Examples include StandUp and Kiss in Hollywood movies. The challenge ca...
Xiao Wu, Chong-Wah Ngo, Jintao Li, Yongdong Zhang
ICPR
2010
IEEE
13 years 5 months ago
Human Activity Recognition Using Local Shape Descriptors
We propose a method for human activity recognition in videos, based on shape analysis. We define local shape descriptors for interest points on the detected contour of the human a...
Sharath Venkatesha, Matthew Turk
ICIP
2009
IEEE
14 years 6 months ago
Recognizing Human Actions By Fusing Spatio-temporal Appearance And Motion Descriptors
In this paper we propose a new method for human action categorization by using an effective combination of a new 3D gradient descriptor with an optic flow descriptor, to represent...