research-article

Exploring the influence of motion boundary sampling to improved dense trajectories for action recognition

Authors:

Jianhui WuAuthors Info & Claims

ICIMCS '15: Proceedings of the 7th International Conference on Internet Multimedia Computing and Service

Article No.: 62, Pages 1 - 5

https://doi.org/10.1145/2808492.2808554

Published: 19 August 2015 Publication History

Abstract

This paper addresses the problem of action recognition. Recently, Wang et al. [11] proposed an approach to describe videos by improved dense trajectories (IDT) which has a significant improvement over the state of the art on some realistic data sets with fisher vectors (FVs). However, IDT is very dense and computationally complex for extracting video-level representation. Therefore, we adopt motion boundary sampling to reduce memory and computation cost, and explore how this sampling method influence mean average precision (mAP). We evaluate motion boundary sampling on KTH, Youtube, and HMDB51 dataset, and as a result, the number of the trajectories is significantly reduced compared to IDT. What's more, the performance of this method is similar to IDT with the framework of [14].

References

[1]

J. Cho, M. Lee, H. Jin Chang, and S. Oh. Robust action recognition using local motion and group sparsity. Pattern Recognition, 2013.

Digital Library

[2]

J. Kittler, M. Hatef, R. P. Duin, and J. Matas. On combining classifiers. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 20(3):226--239, 1998.

Digital Library

[3]

H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, and T. Serre. Hmdb: a large video database for human motion recognition. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 2556--2563. IEEE.

Digital Library

[4]

J. Liu, J. Luo, and M. Shah. Recognizing realistic actions from videos ąřin the wildąś. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 1996--2003. IEEE.

[5]

O. R. Murthy and R. Goecke. Ordered trajectories for large scale human action recognition. In IEEE Intenational Conference on Computer Vision Workshops (ICCV2013), volume 4321.

Digital Library

[6]

X. Peng, Y. Qiao, Q. Peng, and X. Qi. Exploring motion boundary based sampling and spatial-temporal context descriptors for action recognition. In Proc. BMVC, pages 1--11.

[7]

F. Perronnin and C. Dance. Fisher kernels on visual vocabularies for image categorization. In Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on, pages 1--8. IEEE.

[8]

F. Perronnin, J. Síćnchez, and T. Mensink. Improving the fisher kernel for large-scale image classification, pages 143--156. Springer, 2010.

Digital Library

[9]

H. Wang, A. Klaser, C. Schmid, and C.-L. Liu. Action recognition by dense trajectories. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 3169--3176. IEEE.

Digital Library

[10]

H. Wang, A. Kl?ser, C. Schmid, and C.-L. Liu. Dense trajectories and motion boundary descriptors for action recognition. International Journal of Computer Vision, pages 1--20, 2013.

[11]

H. Wang and C. Schmid. Action recognition with improved trajectories. In International Conference on Computer Vision, 2013.

Digital Library

[12]

H. Wang, M. M. Ullah, A. Klaser, I. Laptev, and C. Schmid. Evaluation of local spatio-temporal features for action recognition. In BMVC 2009-British Machine Vision Conference.

[13]

X. Wu, D. Xu, L. Duan, and J. Luo. Action recognition using context and appearance distribution features. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 489--496. IEEE.

Digital Library

[14]

H. Xu, Q. Tian, Z. Wang, and J. Wu. Evaluation of different dimensionality reduction techniques and learning methods for action recognition. In IET Computer Vision.

[15]

H. Xu, Q. Tian, Z. Wang, and J. Wu. Human action recognition using late fusion and dimensionality reduction. In Digital Signal Processing (DSP), 2014 19th International Conference on, pages 63--67. IEEE.

[16]

H. Xu, Q. Tian, Z. Wang, and J. Wu. A survey on aggregating methods for action recognition with dense trajectories. In Multimedia tools and applications, 2015.

Cited By

Verrini FCrispim-Junior CChessa MSolari FBremond F(2018)Recognition of Daily Activities by embedding hand-crafted features within a semantic analysis2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS)10.1109/IPAS.2018.8708854(210-215)Online publication date: Dec-2018
https://doi.org/10.1109/IPAS.2018.8708854
Xu HTian QWang ZWu J(2016)A joint evaluation of different dimensionality reduction techniques, fusion and learning methods for action recognitionNeurocomputing10.1016/j.neucom.2016.06.017214:C(329-339)Online publication date: 19-Nov-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.06.017

Index Terms

Exploring the influence of motion boundary sampling to improved dense trajectories for action recognition
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks
        Video summarization

Recommendations

Global Contrast Based Salient Region Boundary Sampling for Action Recognition
MMM 2016: Proceedings, Part I, of the 22nd International Conference on MultiMedia Modeling - Volume 9516

Although the excellent representation ability of improved Dense Trajectory iDT based features for action video had been proved on several action datasets, the performance of action recognition still suffers from large camera motion of videos. In this ...
Action Recognition Based on Dense Action Captioning
ICDIP '23: Proceedings of the 15th International Conference on Digital Image Processing

Considering that visually similar actions may be easily distinguished in textual description, it provides an opportunity to introduce textual description to assist action recognition. This paper proposes a novel action recognition method based on dense ...
Human action and event recognition using a novel descriptor based on improved dense trajectories

We propose a unified method for recognizing human action and human related events in a realistic video. We use an efficient pipeline of (a) a 3D representation of the Improved Dense Trajectory Feature (DTF) and (b) Fisher Vector (FV). Further, a novel ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICIMCS '15: Proceedings of the 7th International Conference on Internet Multimedia Computing and Service

August 2015

397 pages

ISBN:9781450335287

DOI:10.1145/2808492

General Chairs:
Ramesh Jain
University of California, Irvine
,
Shuqiang Jiang
Institute of Computing Technology, Chinese Academy of Sciences, China
,
Program Chairs:
John Smith
IBM Thomas J. Watson Research Center
,
Jitao Sang
Institute of Automation, Chinese Academy of Sciences, China
,
Guohui Li
National University of Defense Technology, China

Copyright © 2015 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 August 2015

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

ICIMCS '15

ICIMCS '15: International Conference on Internet Multimedia Computing and Service

August 19 - 21, 2015

Hunan, Zhangjiajie, China

Acceptance Rates

ICIMCS '15 Paper Acceptance Rate 20 of 128 submissions, 16%;

Overall Acceptance Rate 163 of 456 submissions, 36%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
79
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 03 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Verrini FCrispim-Junior CChessa MSolari FBremond F(2018)Recognition of Daily Activities by embedding hand-crafted features within a semantic analysis2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS)10.1109/IPAS.2018.8708854(210-215)Online publication date: Dec-2018
https://doi.org/10.1109/IPAS.2018.8708854
Xu HTian QWang ZWu J(2016)A joint evaluation of different dimensionality reduction techniques, fusion and learning methods for action recognitionNeurocomputing10.1016/j.neucom.2016.06.017214:C(329-339)Online publication date: 19-Nov-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.06.017

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten