Human Action Recognition Using Maximum Temporal Inter-Class Dissimilarity

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 246)


Human action sequences can be considered as nonlinear dynamic manifolds in image frames space. In this paper, a novel manifold embedding method, Maximum Temporal Inter-class Dissimilarity (MTID), is proposed for human action recognition, which is based on the framework of Locality Preserving Projections (LPP). Being different from LPP whose goal is to minimize the intra-class distance in local neighborhood, MTID can make best of both the class label information and the temporal information to maximize the inter-class distance in local neighborhood, Namely, focusing on maximizing the dissimilarity between frames that are similar in appearance but are from different classes. At last the Nearest Neighbors classifier based on Hausdorff distance is introduced for recognition. The experimental results demonstrate the effectiveness of the proposed method for human action recognition.


Human action recognition Manifold learning Maximum temporal inter-class dissimilarity 



This research is supported by National Natural Science Foundation of China (61201271), Specialized Research Fund for the Doctoral Program of Higher Education (20100185120021), and Sichuan science and technology support program (cooperated with Chinese Academy of Sciences) (2012JZ0001).


  1. 1.
    Jia K, Yeung D (2008) Human action recognition using local spatio-temporal discriminant embedding. IEEE Conf Comput Vis Pattern Recogn 1–8Google Scholar
  2. 2.
    Wang L, Suter D (2007) Learning and matching of dynamic shape manifolds for human action recognition. IEEE Trans Image Process 16(6):1646–1661CrossRefMathSciNetGoogle Scholar
  3. 3.
    He X, Niyogi P (2004) Locality preserving projections. Neural Inform Process Syst 16:153–160Google Scholar
  4. 4.
    Blackburn J, Ribeiro E (2007) Human motion recognition using isomap and dynamic time warping. In: International conference on computer vision workshop on human motion, pp 285–298Google Scholar
  5. 5.
    Lewandowski M, Martinez-del-Rincon J, Makris D, Nebe J (2010) Temporal extension of laplacian eigenmaps for unsupervised dimensionality reduction of time series. Int Conf Pattern Recogn 161–164Google Scholar
  6. 6.
    Fang C, Chen J, Tseng C, Lien J (2009) Human action recognition using spatio-temporal classification. Asian Conf Comput Vis 98–109Google Scholar
  7. 7.
    Zheng Z, Yanga F, Tana W, Jiaa J, Yangb J (2007) Gabor feature-based face recognition using supervised locality preserving projection. Signal Process 87(10):2473–2483CrossRefMATHGoogle Scholar
  8. 8.
    Kokiopoulou E, Saad Y (2007) Orthogonal neighborhood preserving projections: A projection-based dimensionality reduction technique. IEEE Trans Pattern Anal Mach Intell 29(12):2143–2156CrossRefGoogle Scholar
  9. 9.
    Wang L, Suter D (2008) Visual learning and recognition of sequential data manifolds with applications to human movement analysis. Comput Vis Image Understand 110(2):153–172CrossRefGoogle Scholar
  10. 10.
    Gorelick L, Blank M, Shechtman E, Irani M, Basri R (2007) Action as space-time shapes. IEEE Trans Pattern Anal Mach Intell 29(12):2247–2253CrossRefGoogle Scholar
  11. 11.
    Cai D, He X, Zhou K (2007) Locality sensitive discriminant analysis. Int Joint Conf Artif Intell 708–713Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.School of Electronic EngineeringUniversity of Electronic Science and Technology of ChinaChengduChina

Personalised recommendations