A compact representation of human actions by sliding coordinate coding
Human action recognition remains challenging in realistic videos, where scale and viewpoint changes make the problem complicated. Many complex models have been developed to overcome these difficulties, while we explore using low-level features and typical classifiers to achieve the state-of-the-art...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2018
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/87514 http://hdl.handle.net/10220/44460 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-87514 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-875142020-03-07T13:57:31Z A compact representation of human actions by sliding coordinate coding Ding, Runwei Sun, Qianru Liu, Mengyuan Liu, Hong School of Electrical and Electronic Engineering Human Action Recognition Bag-of-words Model Human action recognition remains challenging in realistic videos, where scale and viewpoint changes make the problem complicated. Many complex models have been developed to overcome these difficulties, while we explore using low-level features and typical classifiers to achieve the state-of-the-art performance. The baseline model of feature encoding for action recognition is bag-of-words model, which has shown high efficiency but ignores the arrangement of local features. Refined methods compensate for this problem by using a large number of co-occurrence descriptors or a concatenation of the local distributions in designed segments. In contrast, this article proposes to encode the relative position of visual words using a simple but very compact method called sliding coordinates coding (SCC). The SCC vector of each kind of word is only an eight-dimensional vector which is more compact than many of the spatial or spatial–temporal pooling methods in the literature. Our key observation is that the relative position is robust to the variations of video scale and view angle. Additionally, we design a temporal cutting scheme to define the margin of coding within video clips, since visual words far away from each other have little relationship. In experiments, four action data sets, including KTH, Rochester Activities, IXMAS, and UCF YouTube, are used for performance evaluation. Results show that our method achieves comparable or better performance than the state of the art, while using more compact and less complex models. Published version 2018-02-28T04:50:07Z 2019-12-06T16:43:31Z 2018-02-28T04:50:07Z 2019-12-06T16:43:31Z 2017 Journal Article Ding, R., Sun, Q., Liu, M., & Liu, H. (2017). A compact representation of human actions by sliding coordinate coding. International Journal of Advanced Robotic Systems, 14(6), 1-12. 1729-8806 https://hdl.handle.net/10356/87514 http://hdl.handle.net/10220/44460 10.1177/1729881417746114 en International Journal of Advanced Robotic Systems © 2017 The Author(s). Creative Commons CC BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License (http://www.creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage). 12 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Human Action Recognition Bag-of-words Model |
spellingShingle |
Human Action Recognition Bag-of-words Model Ding, Runwei Sun, Qianru Liu, Mengyuan Liu, Hong A compact representation of human actions by sliding coordinate coding |
description |
Human action recognition remains challenging in realistic videos, where scale and viewpoint changes make the problem complicated. Many complex models have been developed to overcome these difficulties, while we explore using low-level features and typical classifiers to achieve the state-of-the-art performance. The baseline model of feature encoding for action recognition is bag-of-words model, which has shown high efficiency but ignores the arrangement of local features. Refined methods compensate for this problem by using a large number of co-occurrence descriptors or a concatenation of the local distributions in designed segments. In contrast, this article proposes to encode the relative position of visual words using a simple but very compact method called sliding coordinates coding (SCC). The SCC vector of each kind of word is only an eight-dimensional vector which is more compact than many of the spatial or spatial–temporal pooling methods in the literature. Our key observation is that the relative position is robust to the variations of video scale and view angle. Additionally, we design a temporal cutting scheme to define the margin of coding within video clips, since visual words far away from each other have little relationship. In experiments, four action data sets, including KTH, Rochester Activities, IXMAS, and UCF YouTube, are used for performance evaluation. Results show that our method achieves comparable or better performance than the state of the art, while using more compact and less complex models. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Ding, Runwei Sun, Qianru Liu, Mengyuan Liu, Hong |
format |
Article |
author |
Ding, Runwei Sun, Qianru Liu, Mengyuan Liu, Hong |
author_sort |
Ding, Runwei |
title |
A compact representation of human actions by sliding coordinate coding |
title_short |
A compact representation of human actions by sliding coordinate coding |
title_full |
A compact representation of human actions by sliding coordinate coding |
title_fullStr |
A compact representation of human actions by sliding coordinate coding |
title_full_unstemmed |
A compact representation of human actions by sliding coordinate coding |
title_sort |
compact representation of human actions by sliding coordinate coding |
publishDate |
2018 |
url |
https://hdl.handle.net/10356/87514 http://hdl.handle.net/10220/44460 |
_version_ |
1681043729069113344 |