Learning spatio-temporal co-occurrence correlograms for efficient human action classification
Spatio-temporal interest point (STIP) based features show great promises in human action analysis with high efficiency and robustness. However, they typically focus on bag-of-visual words (BoVW), which omits any correlation among words and shows limited discrimination in real-world videos. In this p...
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2013
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4465 https://ink.library.smu.edu.sg/context/sis_research/article/5468/viewcontent/Template.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-5468 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-54682019-11-28T07:46:27Z Learning spatio-temporal co-occurrence correlograms for efficient human action classification SUN, Qianru LIU, Hong Spatio-temporal interest point (STIP) based features show great promises in human action analysis with high efficiency and robustness. However, they typically focus on bag-of-visual words (BoVW), which omits any correlation among words and shows limited discrimination in real-world videos. In this paper, we propose a novel approach to add the spatio-temporal co-occurrence relationships of visual words to BoVW for a richer representation. Rather than assigning a particular scale on videos, we adopt the normalized google-like distance (NGLD) to measure the words' co-occurrence semantics, which grasps the videos' structure information in a statistical way. All pairwise distances in spatial and temporal domain compose the corresponding NGLD correlograms, then their united form is incorporated with BoVW by training a multi-channel kernel SVM classifier. Experiments on real-world datasets (KTH and UCF sports) validate the efficiency of our approach for the classification of human actions. 2013-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4465 info:doi/10.1109/ICIP.2013.6738663 https://ink.library.smu.edu.sg/context/sis_research/article/5468/viewcontent/Template.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Human action recognition spatio-temporal interest points bag-of-words co-occurrence Computer Engineering Software Engineering |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Human action recognition spatio-temporal interest points bag-of-words co-occurrence Computer Engineering Software Engineering |
spellingShingle |
Human action recognition spatio-temporal interest points bag-of-words co-occurrence Computer Engineering Software Engineering SUN, Qianru LIU, Hong Learning spatio-temporal co-occurrence correlograms for efficient human action classification |
description |
Spatio-temporal interest point (STIP) based features show great promises in human action analysis with high efficiency and robustness. However, they typically focus on bag-of-visual words (BoVW), which omits any correlation among words and shows limited discrimination in real-world videos. In this paper, we propose a novel approach to add the spatio-temporal co-occurrence relationships of visual words to BoVW for a richer representation. Rather than assigning a particular scale on videos, we adopt the normalized google-like distance (NGLD) to measure the words' co-occurrence semantics, which grasps the videos' structure information in a statistical way. All pairwise distances in spatial and temporal domain compose the corresponding NGLD correlograms, then their united form is incorporated with BoVW by training a multi-channel kernel SVM classifier. Experiments on real-world datasets (KTH and UCF sports) validate the efficiency of our approach for the classification of human actions. |
format |
text |
author |
SUN, Qianru LIU, Hong |
author_facet |
SUN, Qianru LIU, Hong |
author_sort |
SUN, Qianru |
title |
Learning spatio-temporal co-occurrence correlograms for efficient human action classification |
title_short |
Learning spatio-temporal co-occurrence correlograms for efficient human action classification |
title_full |
Learning spatio-temporal co-occurrence correlograms for efficient human action classification |
title_fullStr |
Learning spatio-temporal co-occurrence correlograms for efficient human action classification |
title_full_unstemmed |
Learning spatio-temporal co-occurrence correlograms for efficient human action classification |
title_sort |
learning spatio-temporal co-occurrence correlograms for efficient human action classification |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2013 |
url |
https://ink.library.smu.edu.sg/sis_research/4465 https://ink.library.smu.edu.sg/context/sis_research/article/5468/viewcontent/Template.pdf |
_version_ |
1770574847173197824 |