Sciweavers

96 search results - page 8 / 20
» Content based video matching using spatiotemporal volumes
Sort
View
CVPR
2009
IEEE
15 years 2 months ago
Topology Dictionary with Markov Model for 3D Video Content-Based Skimming and Description
This paper presents a novel approach to skim and describe 3D videos. 3D video is an imaging technology which consists in a stream of 3D models in motion captured by a synchronized ...
Tony Tung (Kyoto University), Takashi Matsuyama (K...
ICCV
2011
IEEE
12 years 7 months ago
A String of Feature Graphs Model for Recognition of Complex Activities in Natural Videos
Videos usually consist of activities involving interactions between multiple actors, sometimes referred to as complex activities. Recognition of such activities requires modeling ...
Utkarsh Gaur, Yingying Zhu, Bi Song, Amit Roy-Chow...
ICASSP
2007
IEEE
13 years 11 months ago
Adaptive Multi-Pattern Fast Block-Matching Algorithm Based on Motion Classification Techniques
Motion estimation is the most time-consuming subsystem in a video codec. Thus, more efficient methods of motion estimation should be investigated. Real video sequences usually exh...
Iván González-Díaz, Manuel de...
ICPR
2000
IEEE
14 years 8 months ago
EPI Analysis of Omni-Camera Image
This paper describes an efficient method to obtain 3D information from omni images using EPI analysis. Two types of omni cameras are employed to make a spatio-temporal volume, whi...
Hiroshi Kawasaki, Katsushi Ikeuchi, Masao Sakauchi
CVPR
2008
IEEE
14 years 9 months ago
Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition
In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A...
Mikel D. Rodriguez, Javed Ahmed, Mubarak Shah