Human action recognition with sparse geometric features

References

• Maji S, Bourdev L and Malik J. Action recognition from a distributed representation of pose and appearance, Proc. 4th IEEE Conf. on Computer vision and pattern recognition: CVPR 2011, Colorado Springs, CO, USA, June 2011, IEEE, pp. 3177–3184.
   Google Scholar
• Liu C and Yuen PC. Human action recognition using boosted EigenActions. Image Vis. Comput., 2010, 28, 825–835.
   Web of Science ®Google Scholar
• Wang J, Liu P, Kouzani A and Nahavandi S. Human action recognition based on pyramid histogram of oriented gradients, Proc. 2011 IEEE Int. Conf. on Systems, man, and cybernetics: SMC 2011, Anchorage, AK, USA, October 2011, IEEE, pp. 2449–2454.
   Google Scholar
• Yao BP, Jiang XY, Khosla A., Lin A.Y., Guibas L. and Li F.-F. Human action recognition by learning bases of action attributes and parts, Proc. 2011 IEEE Int. Conf. on Computer vision: ICCV 2011, Barcelona, Spain, November 2011, IEEE, pp. 1331–1338.
   Google Scholar
• Gavrila DM and Davis LS. 3D model-based tracking of humans in action: a multi-view approach, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition: CVPR 2004, Washington, DC, USA, June 1996, IEEE, pp. 73–80.
   Google Scholar
• Wang SQ, Huang KQ and Tan TN. A compact optical flow based motion representation for real-time action recognition in surveillance scenes, Proc. Int. Conf. on Image processing: ICIP 2009, Cairo, Egypt, November 2009, IEEE, pp. 1121–1124.
   Google Scholar
• Laptev I and Lindeberg T. Space–time interest points, Proc. 9th IEEE Int. Conf. on Computer vision: ICCV 2003, Nice, France, October 2003, IEEE, pp. 432–439.
   Google Scholar
• Scovanner P, Ali S and Shah M. A 3-dimensional SIFT descriptor and its application to action recognition, Proc. ACM Conf. Multimedia, Augsburg, Germany, September 2007, ACM, pp. 357–360.
   Google Scholar
• Klaser A, Marszalek M and Schmid C. A spatio-temporal descriptor based on 3D-gradients, Proc. British Machine Vision Conf.: BMVC, Leeds, UK, September 2008, BMAV, pp. 995–1004.
   Google Scholar
• Gilbert A, Illingworth J and Bowden R. Scale invariant action recognition using compound features mined from dense spatio-temporal corners, Proc. 10th European Conf. on Computer vision: ECCV 2008, Marseille, France, October 2008, INRIA, pp. 222–233.
   Google Scholar
• Wu QX, Lu SY, Wang ZY and Deng FQ. Structure context of local features in realistic human action recognition, Proc. Int. Conf. on Computer vision: ICCV 2011, Barcelona, Spain, November 2011, IEEE, pp. 1496–1501.
   Google Scholar
• Bobick AF and Davis JW. The recognition of human movement using temporal templates. IEEE Trans. PAMI, 2001, 23, 257–267.
   Web of Science ®Google Scholar
• Dalal N and Triggs B. Histograms of oriented gradients for human detection, Proc. IEEE Conf. on Computer vision and pattern recognition, San Diego, CA, USA, June 2005, IEEE, pp. 886–893.
   Google Scholar
• Thurau C and Hlavac V. Pose primitive based human action recognition in video or still images, Proc. 2008 IEEE Conf. on Computer vision and pattern recognition, Anchorage, AK, USA, June 2008, IEEE, pp. 1–6.
   Google Scholar
• Yamato J, Ohya J and Ishii K. Recognizing human action in time-sequential images using hidden Markov model, Proc. 1992 IEEE Conf. on Computer vision and pattern recognition, Yokosuka, Japan, June 1992, IEEE, pp. 379–385.
   Google Scholar
• Le Pennec E and Mallat S. Sparse geometric image representations with Bandelets. IEEE Trans. IP, 2005, 14, 423–438.
   Web of Science ®Google Scholar
• Peyre G and Mallat S. Discrete Bandelets with geometric orthogonal filters, Proc. 2005 IEEE Int. Conf. on Image processing, Genoa, Italy, September 2005, IEEE, pp. 65–68.
   Google Scholar
• Rosset S, Zhu J, Hastie T and Zou H. Multi-class AdaBoost. Stat. Its Interface, 2009, 2, 349–360.
   Web of Science ®Google Scholar
• Schapire RE and Singer Y. BoosTexter: a boosting-based system for text categorization. Mach. Learn., 2000, 39, 135–168.
   Web of Science ®Google Scholar
• Shen LL and Bai L. AdaBoost Gabor feature selection for classification, Proc. Image and Vision Computing Conf., Singapore, 2004, IEEE, pp. 77–83.
   Google Scholar
• Sun C, Hu JW and Lam K.-M. Feature subset selection for efficient AdaBoost training, Proc. 2011 IEEE Int. Conf. on Multimedia and expo, Barcelona, Spain, July 2011, IEEE, pp. 1–6.
   Google Scholar
• Chiu LK, Gestner B and Anderson D V. Design of analog audio classifiers with AdaBoost-Based feature selection, Proc. Int. Symp. on Circuits and systems: ISCAS 2011, Rio de Janeiro, Brazil, May 2011, IEEE, pp. 2469–2472.
   Google Scholar
• Available at: <http://www.wisdom.weizmann.ac.il/∼vision/SpaceTimeActions.html>
   Google Scholar
• Available at: <http://www.nada.kth.se/cvap/actions/>
   Google Scholar
• Chang C.-C and Lin CJ. LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol., 2011, 2, 27.
   Web of Science ®Google Scholar
• Dollar P, Rabaud V and Cottrell G. Behavior recognition via sparse spatio-temporal features, Proc. 14th Int. Conf. on Computer communications and networks, San Diego, CA, USA, October 2005, ACM, pp. 65–72.
   Google Scholar
• Ali S, Basharat A and Shah M. Chaotic invariants for human action recognition, Proc. IEEE 11th Int. Conf. on Computer vision: ICCV 2007, Rio de Janeiro, Brazil, October 2007, IEEE, pp. 1–8.
   Google Scholar
• Niebles JC and FeiFei L. A hierarchical model of shape and appearance for human action classification, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, Minneapolis, MN, USA, June 2007, IEEE, pp. 1–8.
   Google Scholar
• Thurau C and Hlavac V. Pose primitive based human action recognition in videos or still images, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, Anchorage, AK, USA, June 2008, IEEE. 1–8.
   Google Scholar
• Zhang Z, Hu Y and Chan S. Motion context: a new representation for human action recognition. Lect. Notes Comput. Sci., 2008, 5305, 817–829.
   Google Scholar
• Mauthner T, Roth PM and Bischof H. Instant action recognition, Proc. Scandinavian Conf. on Image analysis, Oslo, Norway, June 2009, Pattern Recognition Society of Finland. 1–10.
   Google Scholar
• Ali S and Shah M. Human action recognition in videos using kinematic features and multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, 288–303.
   PubMed Web of Science ®Google Scholar
• Available at: <http://pascal.inrialpes.fr/data/human/> (accessed 21 January 2011).
   Google Scholar
• Acar E, Senst T and Kuhn A. Human action recognition using Lagrangian descriptors, Proc. 2012 IEEE 14th Int. Workshop on Multimedia signal processing, Banff, Canada, September 2012, IEEE. 360–365.
   Google Scholar
• Schuldt C, Laptev I and Caputo B. Recognizing human actions: a local SVM approach, Proc. 17th International Conference on Pattern Recognition, Cambridge, UK, August 2004, IEEE, Vol. 3, pp. 32–36.
   Google Scholar
• Kim T, Wong S and Cipolla R. Tensor canonical correlation analysis for action classification, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, Minneapolis, MN, USA, June 2007, IEEE, pp. 1–8.
   Google Scholar
• Laptev I, Marsza’ek M, Schmid C and Rozenfeld B. Learning realistic human actions from movies, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, Anchorage, AK, USA, June 2008, IEEE, pp. 1–8.
   Google Scholar
• Liu J, Luo J and Shah M. Recognizing realistic actions from videos ‘‘in the wild’, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, Miami, FL, USA, June 2009, pp. 1996–2003.
   Google Scholar
• Yao A, Gall J and van Gool L. A Hough transform-based voting framework for action recognition, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, San Francisco, CA, USA, June 2010, IEEE, pp. 2061–2068.
   Google Scholar
• Kovashka A and Grauman K. Learning a hierarchy of discriminative space-time neighborhood features for human action recognition, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, San Francisco, CA, USA, June 2010, IEEE, pp. 2046–2053.
   Google Scholar
• Cao L, Liu Z and Huang T. Cross-dataset action detection, Proc. IEEE Computer Society Conf. on Computer vision and pattern recognition, San Francisco, CA, USA, June 2010, IEEE, pp. 1998–2005.
   Google Scholar