skip to main content
10.1145/2499788.2499843acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicimcsConference Proceedingsconference-collections
research-article

Sparse representation for recognizing object-to-object actions under occlusions

Published: 17 August 2013 Publication History

Abstract

In this paper, we describe the formatting guidelines for ACM SIG Proceedings. This paper proposes a novel event classification scheme to analyze various interaction actions between persons using sparse representation. The occlusion problem and the high complexity to model complicated interactions are two major challenges in person-to-person action analysis. To address the occlusion problem, the proposed scheme represents an action sample in an over-complete dictionary whose base elements are the training samples themselves. This representation is naturally sparse and makes errors (caused by different environmental changes like lighting or occlusions) sparsely appear in the training library. Because of the sparsity, it is robust to occlusions and lighting changes. In addition, a novel Hamming distance classification (HDC) scheme is proposed to classify action events to detailed types. Because the nature of Hamming code is highly tolerant to noise, the HDC scheme is also robust to occlusions. The high complexity of complicated action modeling can be tackled by adding more examples to the over-complete dictionary. Thus, even though the interaction relations are complicated, the proposed method still works successfully to recognize them and can be easily extended to analyze action events among multiple persons. More importantly, the HDC scheme is very efficient and suitable for real-time applications because no optimization process is involved to calculate the reconstruction error.

References

[1]
Weinland, D., Ronfard, R., and Boyer, E. 2011. A survey of vision-based methods for action representation, segmentation, and recognition. Computer Vision and Image Understanding. 115, (2011), 224--241.
[2]
Aharon, M., Elad, E., and Bruckstein, A. 2006. K-svd: An algorithm for designing overcomplete dictionries for sparse representation. IEEE Trans. on Signal Processing. (2006), 4311--4322.
[3]
Mairal, J., Bach, F., Ponce, J., and Sapiro, G. 2010. Online learning for matrix factorization and sparse coding. J. Mach. Learn. Res. 11, (2010) 19--60.
[4]
Wang, Y., Huang, K. and Tan, T. 2007. Human activity recognition based on R transform. CVPR (2007).
[5]
Cong, Y., Yuan, J., and Liu, J. 2011. Sparse Reconstruction Cost for Abnormal Event Detection. CVPR (2011).
[6]
Mahajan, D., Kwatra, N., Jain, S., and Kalra, P. 2004. A framework for activity recognition and detection of unusual activities. International Conference on Graphic and Image Processing (2004).
[7]
Gaidon, A., Harchaoui, Z., and Schmid, C. 2011. Actom Sequence Models for Efficient Action Detection. CVPR, (2011).
[8]
Fathi A. and Mori, G. 2008. Action recognition by learning mid-level motion features. CVPR (Jun. 2008), 1--8.
[9]
Ju, S., et al. 2009. Hierarchical Spatio-Temporal Context Modeling for Action Recognition. CVPR (2009) 2004--2011.
[10]
Messing, R. Pal, C. and Kautz, H. 2009. Activity recognition using the velocity histories of tracked keypoints. International Conference on Computer Vision (2009).
[11]
Yao, B. and Fei-Fei, L. 2012. Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses. IEEE Transactions on PAMI. 34, 9 (Sep. 2012), 1691--1703.
[12]
Yao B. and Fei-Fei, L. Grouplet: a structure image representation for recognizing human and object interactions. CVPR (2010).
[13]
Filipovych R. and Ribeiro, E. 2008. Recognizing Primitive Interactions by Exploring Actor-Object States. CVPR (Jun. 2008), 1--7.

Cited By

View all
  • (2016)Negative Correlation Discovery for Big Multimedia Data Semantic Concept Mining and Retrieval2016 IEEE Tenth International Conference on Semantic Computing (ICSC)10.1109/ICSC.2016.73(55-62)Online publication date: Feb-2016
  • (2015)Spatio-Temporal Analysis for Human Action Detection and Recognition in Uncontrolled EnvironmentsInternational Journal of Multimedia Data Engineering and Management10.4018/ijmdem.20150101016:1(1-18)Online publication date: Jan-2015

Index Terms

  1. Sparse representation for recognizing object-to-object actions under occlusions

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      ICIMCS '13: Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
      August 2013
      419 pages
      ISBN:9781450322522
      DOI:10.1145/2499788
      • Conference Chair:
      • Tat-Seng Chua,
      • General Chairs:
      • Ke Lu,
      • Tao Mei,
      • Xindong Wu
      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]

      Sponsors

      • NSF of China: National Natural Science Foundation of China
      • University of Sciences & Technology, Hefei: University of Sciences & Technology, Hefei
      • Beijing ACM SIGMM Chapter

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 17 August 2013

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. action analysis
      2. hamming distance classification
      3. occlusions
      4. sparse coding

      Qualifiers

      • Research-article

      Conference

      ICIMCS '13
      Sponsor:
      • NSF of China
      • University of Sciences & Technology, Hefei

      Acceptance Rates

      ICIMCS '13 Paper Acceptance Rate 20 of 94 submissions, 21%;
      Overall Acceptance Rate 163 of 456 submissions, 36%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)0
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 13 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2016)Negative Correlation Discovery for Big Multimedia Data Semantic Concept Mining and Retrieval2016 IEEE Tenth International Conference on Semantic Computing (ICSC)10.1109/ICSC.2016.73(55-62)Online publication date: Feb-2016
      • (2015)Spatio-Temporal Analysis for Human Action Detection and Recognition in Uncontrolled EnvironmentsInternational Journal of Multimedia Data Engineering and Management10.4018/ijmdem.20150101016:1(1-18)Online publication date: Jan-2015

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media