A Hierarchical Spatio-Temporal Model for Human Activity Recognition

There are two key issues in human activity recognition: spatial dependencies and temporal dependencies. Most recent methods focus on only one of them, and thus do not have sufficient descriptive power to recognize complex activity. In this paper, we propose a hierarchical spatio-temporal model (HSTM...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2017-07, Vol.19 (7), p.1494-1509
Main Authors: Xu, Wanru, Miao, Zhenjiang, Zhang, Xiao-Ping, Tian, Yi
Format: Article
Language:English
Subjects:
Activity recognition
Aggregates
Classification
Computational modeling
Constraint modelling
Feature extraction
Feature recognition
hidden conditional random field (HCRF)
Hidden Markov models
hierarchical structure
Human activity recognition
Human performance
Machine learning
Modelling
Multimedia communication
Representations
Spatial dependencies
spatio-temporal dependencies
Streaming media
Video sequences
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!