Sciweavers

115 search results - page 6 / 23
» Pairwise Features for Human Action Recognition
Sort
View
JRTIP
2008
300views more  JRTIP 2008»
13 years 7 months ago
Real-time human action recognition on an embedded, reconfigurable video processing architecture
Abstract In recent years, automatic human action recognition has been widely researched within the computer vision and image processing communities. Here we propose a realtime, emb...
Hongying Meng, Michael Freeman, Nick Pears, Chris ...
AMDO
2006
Springer
13 years 11 months ago
Shape-Motion Based Athlete Tracking for Multilevel Action Recognition
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...
Costas Panagiotakis, Emmanuel Ramasso, Georgios Tz...
ACCV
2009
Springer
14 years 2 months ago
Human Action Recognition Using HDP by Integrating Motion and Location Information
The method based on local features has an advantage that the important local motion feature is represented as bag-of-features, but lacks the location information. Additionally, in ...
Yasuo Ariki, Takuya Tonaru, Tetsuya Takiguchi
BMVC
2010
13 years 5 months ago
A Wavelet Based Local Descriptor for Human Action Recognition
In interest point based human action recognition, local descriptors are used to represent information in the neighbourhood around each extracted space-time interest point. The per...
Ling Shao, Ruoyun Gao
ACCV
2009
Springer
14 years 2 months ago
Human Action Recognition Using Pyramid Vocabulary Tree
The bag-of-visual-words (BOVW) approaches are widely used in human action recognition. Usually, large vocabulary size of the BOVW is more discriminative for inter-class action clas...
Chunfeng Yuan, Xi Li, Weiming Hu, Hanzi Wang