Human action recognition in unconstrained videos by explicit motion modeling
Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2015
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6357 https://ink.library.smu.edu.sg/context/sis_research/article/7360/viewcontent/10.1.1.718.4553.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-7360 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-73602021-11-23T03:46:02Z Human action recognition in unconstrained videos by explicit motion modeling JIANG, Yu-Gang DAI, Qi LIU, Wei XUE, Xiangyang NGO, Chong-wah Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and object-background relationships are mostly discarded. In this paper, we propose a simple representation aiming at modeling these motion relationships. We adopt global and local reference points to explicitly characterize motion information, so that the final representation is more robust to camera movements, which widely exist in unconstrained videos. Our approach operates on the top of visual codewords generated on dense local patch trajectories, and therefore, does not require foreground-background separation, which is normally a critical and difficult step in modeling object relationships. Through an extensive set of experimental evaluations, we show that the proposed representation produces a very competitive performance on several challenging benchmark data sets. Further combining it with the standard bag-of-features or Fisher vector representations can lead to substantial improvements. 2015-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6357 info:doi/10.1109/TIP.2015.2456412 https://ink.library.smu.edu.sg/context/sis_research/article/7360/viewcontent/10.1.1.718.4553.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 trajectory motion representation reference points camera motion Computer Sciences Graphics and Human Computer Interfaces |
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 trajectory motion representation reference points camera motion Computer Sciences Graphics and Human Computer Interfaces |
spellingShingle |
Human action recognition trajectory motion representation reference points camera motion Computer Sciences Graphics and Human Computer Interfaces JIANG, Yu-Gang DAI, Qi LIU, Wei XUE, Xiangyang NGO, Chong-wah Human action recognition in unconstrained videos by explicit motion modeling |
description |
Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and object-background relationships are mostly discarded. In this paper, we propose a simple representation aiming at modeling these motion relationships. We adopt global and local reference points to explicitly characterize motion information, so that the final representation is more robust to camera movements, which widely exist in unconstrained videos. Our approach operates on the top of visual codewords generated on dense local patch trajectories, and therefore, does not require foreground-background separation, which is normally a critical and difficult step in modeling object relationships. Through an extensive set of experimental evaluations, we show that the proposed representation produces a very competitive performance on several challenging benchmark data sets. Further combining it with the standard bag-of-features or Fisher vector representations can lead to substantial improvements. |
format |
text |
author |
JIANG, Yu-Gang DAI, Qi LIU, Wei XUE, Xiangyang NGO, Chong-wah |
author_facet |
JIANG, Yu-Gang DAI, Qi LIU, Wei XUE, Xiangyang NGO, Chong-wah |
author_sort |
JIANG, Yu-Gang |
title |
Human action recognition in unconstrained videos by explicit motion modeling |
title_short |
Human action recognition in unconstrained videos by explicit motion modeling |
title_full |
Human action recognition in unconstrained videos by explicit motion modeling |
title_fullStr |
Human action recognition in unconstrained videos by explicit motion modeling |
title_full_unstemmed |
Human action recognition in unconstrained videos by explicit motion modeling |
title_sort |
human action recognition in unconstrained videos by explicit motion modeling |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2015 |
url |
https://ink.library.smu.edu.sg/sis_research/6357 https://ink.library.smu.edu.sg/context/sis_research/article/7360/viewcontent/10.1.1.718.4553.pdf |
_version_ |
1770575940969037824 |