Real-time human action recognition by luminance field trajectory analysis

MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops

Volumn , Issue , 2008, Pages 671-675

  Li, Zhu ^a   Fu, Yun ^b   Huang, Thomas S ^b   Yan, Shuicheng ^c  

^a HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

^b UNIVERSITY OF ILLINOIS AT URBANA CHAMPAIGN   (United States)

^c NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Human action recognition; Video analysis; Video understanding

Indexed keywords

COMPUTATIONALLY EFFICIENT; EXPLICIT OBJECTS; EXPLOSIVE GROWTH; HUMAN ACTION RECOGNITION; HUMAN ACTIONS; HUMAN ACTIVITY RECOGNITION; INFORMATION EXTRACTION; LUMINANCE FIELDS; REAL TIME; RECOGNITION PERFORMANCE; SET-UPS; TRAJECTORY ANALYSIS; VIDEO ANALYSIS; VIDEO CONTENTS; VIDEO SEARCHING; VIDEO SURVEILLANCE; VIDEO UNDERSTANDING; VIDEO-CONTENT ANALYSIS;

GESTURE RECOGNITION; METHOD OF MOMENTS; MULTIMEDIA SYSTEMS; VISUAL COMMUNICATION;

SECURITY SYSTEMS;

EID: 70350660670     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/1459359.1459456     Document Type: Conference Paper

References (12)

1. [Chang98] S.-F. Chang, W. Chen, H. J. Meng, H. Sundaram, and D. Zhong, ampquot;A Fully Automated Content-Based Video Search Engine Supporting Spatio-Temporal Queriesampquot; , IEEE Trans on Circuits and Systems for Video Tech (CSVT), vol. 8, no. 5, pp. 602-615, September 1998.
2. [Fu08] Y. Fu, Z. Li, T. S. Huang, and A. K. Katsaggelos. ampquot;Locally Adaptive Subspace and Similarity Metric Learning for Visual Clustering and Retrievalampquot;, Computer Vision and Image Understanding, vol. 110, no. 3, pp. 390-402, 2008.
3. [Ke05] Y. Ke, R. Sukthankar, and M. Hebert. ampquot;Efficient visual event detection using volumetric featuresampquot;, In Proc of IEEE ICCV, pp. 166-173, 2005.
4. [Kim07] T.-Y Kim, S.-F. Wong and R. Cipolla, ampquot;Tensor Canonical Correlation Analysis for Action Classificationampquot;, In Proc. of IEEE Conf. on CVPR, Minneapolis, MN, 2007
5. [Laptev03] L. Laptev and T. Kindeberg, ampquot;Space-time interest pointsampquot;, Proc. of IEEE ICCV, pp. 432-439, Nice, France, 2003.
6. [Belhumeur97] P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, ampquot;Eigenfaces vs. Fisherfaces: recognition using class specific linearprojectionampquot;, IEEE Trans on PAMI, vol. 19, no. 7, pp. 711-720, July 1997.
7. [Li06] Z. Li, L. Gao, A. K. Katsaggelos, ampquot;Locally Embedded Linear Subspaces for Efficient Video Indexing and Retrievalampquot;, Proc. of IEEE Int'l Conf on Multimedia amp Expo, pp. 1765-1768, 2006.
8. [He05] X. He, S. Yan, Y. Hu, P. Niyogi, and H.-J. Zhang, ampquot;Face Recognition Using Laplacianfacesampquot;, IEEE Trans. on PAMI, vol. 27, no. 3, pp. 328-340, Mar. 2005.
9. [Niebles06] J. C. Niebles, H. Wang, and L. Fei-Fei. ampquot;Unsupervised learning of human action categories using spatial-temporal wordsampquot;, Proc of British Machine Vision Conference, Edingburg, 2006.
10. [Schuldt04] C. Schuldt, I. Laptev, and B. Caputo, ampquot;Recognizing Human Actions: A Local SVM Approachampquot;, Proc. of IEEE ICPR, pp. 32-36, Cambridge, UK, 2004.
11. [Yilmaz05] A. Yilmaz and M. Shah. ampquot;Recognizing human actions in videos acquired by uncalibrated moving camerasampquot;, Proc. of IEEE ICCV, vol. 1, pp.150-157, 2005.
12. [Zelnik01]L. Zelnik-Manor and M. Irani, ampquot;Event-based analysis of videoampquot;, Proc. of IEEE CVPR, 2001.