Outdoor Activity Recognition using Multi-Linked Temporal Processes
We develop Dynamically Multi-Linked Hidden Markov Models (DML-HMMs) for interpreting group activities involving multiple objects captured in an outdoor scene. The models are based on the discovery of salient dynamic interlinks among multiple different object events. A layered hierarchical DML-HMM is...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.7977 http://www.comp.leeds.ac.uk/bmvc2008/proceedings/2003/papers/19/paper019.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.385.7977 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.385.7977 2023-05-15T16:01:13+02:00 Outdoor Activity Recognition using Multi-Linked Temporal Processes Tao Xiang Shaogang Gong Dennis Parkinson The Pennsylvania State University CiteSeerX Archives application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.7977 http://www.comp.leeds.ac.uk/bmvc2008/proceedings/2003/papers/19/paper019.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.7977 http://www.comp.leeds.ac.uk/bmvc2008/proceedings/2003/papers/19/paper019.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://www.comp.leeds.ac.uk/bmvc2008/proceedings/2003/papers/19/paper019.pdf text ftciteseerx 2016-09-18T00:32:27Z We develop Dynamically Multi-Linked Hidden Markov Models (DML-HMMs) for interpreting group activities involving multiple objects captured in an outdoor scene. The models are based on the discovery of salient dynamic interlinks among multiple different object events. A layered hierarchical DML-HMM is built using Schwarz’s Bayesian Information Criterion (BIC) based factorisation resulting in its topology being intrinsically determined by the underlying causality and temporal order among different object events. Our experiments demonstrate that the performance of a DML-HMM on modelling group activities in a noisy outdoor scene is superior compared to that of a Coupled Hidden Markov Model (CHMM). Text DML Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
description |
We develop Dynamically Multi-Linked Hidden Markov Models (DML-HMMs) for interpreting group activities involving multiple objects captured in an outdoor scene. The models are based on the discovery of salient dynamic interlinks among multiple different object events. A layered hierarchical DML-HMM is built using Schwarz’s Bayesian Information Criterion (BIC) based factorisation resulting in its topology being intrinsically determined by the underlying causality and temporal order among different object events. Our experiments demonstrate that the performance of a DML-HMM on modelling group activities in a noisy outdoor scene is superior compared to that of a Coupled Hidden Markov Model (CHMM). |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Tao Xiang Shaogang Gong Dennis Parkinson |
spellingShingle |
Tao Xiang Shaogang Gong Dennis Parkinson Outdoor Activity Recognition using Multi-Linked Temporal Processes |
author_facet |
Tao Xiang Shaogang Gong Dennis Parkinson |
author_sort |
Tao Xiang |
title |
Outdoor Activity Recognition using Multi-Linked Temporal Processes |
title_short |
Outdoor Activity Recognition using Multi-Linked Temporal Processes |
title_full |
Outdoor Activity Recognition using Multi-Linked Temporal Processes |
title_fullStr |
Outdoor Activity Recognition using Multi-Linked Temporal Processes |
title_full_unstemmed |
Outdoor Activity Recognition using Multi-Linked Temporal Processes |
title_sort |
outdoor activity recognition using multi-linked temporal processes |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.7977 http://www.comp.leeds.ac.uk/bmvc2008/proceedings/2003/papers/19/paper019.pdf |
genre |
DML |
genre_facet |
DML |
op_source |
http://www.comp.leeds.ac.uk/bmvc2008/proceedings/2003/papers/19/paper019.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.7977 http://www.comp.leeds.ac.uk/bmvc2008/proceedings/2003/papers/19/paper019.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766397174518644736 |