Combining sparse appearance features and dense motion features via random forest for action detection

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2013, Pages 2415-2419

  Yang, Shuang ^a   Yuan, Chunfeng ^a   Wang, Haoran ^b   Hu, Weiming ^a  

^a INSTITUTE OF AUTOMATION   (China)

^b SOUTHEAST UNIVERSITY   (China)

Author keywords

Action detection; Hough voting; Multiple features; Random forest

Indexed keywords

CHANNEL SELECTION; CLASS DISTRIBUTIONS; HOUGH VOTING; LINEAR CLASSIFICATION; LOCATION INFORMATION; MULTIPLE FEATURES; RANDOM FORESTS; STATE-OF-THE-ART PERFORMANCE;

DECISION TREES; FORESTRY; SIGNAL PROCESSING;

FEATURE EXTRACTION;

DECISION MAKING; FORESTRY; TREES;

EID: 84890513604     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6638088     Document Type: Conference Paper

References (27)

1. J. Liu, J. Luo, and M. Shah, "Recognizing Realistic Actionsfrom Videos 'in the Wild'," Proc. IEEE Con! ComputerVision and Pattern Recognition, pp.1996-2003, 2009
2. J. C. Niebles and L. Fei-Fei, "A Hierarchical Model of Shapeand Appearance for Human Action Classification," Proc.IEEE Con! Computer Vision and Pattern Recognition,pp.I-8,2007
3. D. Parikh, C. Zitnick, and T. Chen, "Unsupervised Learningof Hierarchical Spatial Structures in Images," Proc. IEEECon! Computer Vision and Pattern Recognition, pp.2743-2750,2009
4. A Kovashka and K. Grauman, "Learning A Hierarchy ofDiscriminative Space-time Neighborhood Features," Proc.IEEE Con! Computer Vision and Pattern Recognition,pp.2046-2053, 2010
5. J. Laptev and T. Lindeberg, "Space-time Interest Points,"Proc.Int. Conference on Computer Vision, pp.432-439, 2003
6. O. Oshin, A Gilbert, 1. Illingworth and R Bowden, "ActionRecognition Using Randomized Ferns," In Proc. Int.Conference on Computer Vision, pp.530-537, 2009
7. M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri,"Actions as Space-time Shapes," In Proc. Int. Conference onComputer Vision, pp.1395-1402, 2007
8. A Oikonomopoulos, I. Patras, and M. Pantic, "An ImplicitSpatio- temporal Shape Model for Human ActivityLocalization and Recognition," Proc.IEEE Con! ComputerVision and Pattern Recognition, pp.27-33, 2009
9. B. Packer, K. Saenko, and D. Koller, "A Combined Pose,Object and Feature Model for Action Understanding," Proc.IEEE Con! Computer Vision and Pattern Recognition,pp.1378-1385,2012
10. C.Y. Chen and K. Grauman, "Efficient Activity Detectionwith Max-subgraph Search," Proc. IEEE Con! ComputerVision and Pattern Recognition,pp.1274-1281, 2012
11. B. Yao, A Khosla, and L. Fei-Fei, "Combining Randomi-zation and Discrimination for Fine-Grained ImageCategorization," Proc. IEEE Con! Computer Vision andPattern Recognition, pp.1577-1584, 2011
12. H.Wang, AKlaser, C. Schmid, and C.L.Liu. "ActionRecognition by Dense Trajectories," Proc. IEEE Con!Computer Vision and Pattern Recognition, pp.3169-3176,2011
13. J. Gall and V. Lempitsky, "Class-Specific Hough Forests forObject Detection," Proc. IEEE Con! Computer Vision andPattern Recognition, pp.l 022-1029,2009
14. K. Mikolajczyk and H. Uemura, "Action Recognition withMotion-appearance Vocabulary Forest," Proc. IEEE Con!Computer Vision and Pattern Recognition, ppl-8,2008
15. Z. Lin, Z. Jian, and L.S.Davis, "Recognizing Actions byShape-motion Prototype trees," Proc. Int. Conference onComputer Vision, pp.444-451, 2009
16. Marcenaro, L., Marchesotti, L., Regazzoni, C.S., "Self-organizing shape description for tracking and classifyingmultiple interacting objects, " Image and Vision Computing,24 (11), pp.l 179-1 191,2006
17. AYao, lGall, and L. Van Gool, "A Hough Transform-BasedVoting Framework for Action Recognition," Proc. IEEECon! Computer Vision and Pattern Recognition, pp.2061-2068,2010
18. L. Breiman, "Random Forests," Machine Learning, pp.5-32,2001
19. P. Scovanner, S. Ali and M. Shah, "A 3-dimensional SIFTDescriptor and Its Application to Action Recognition,"Proceedings of the International Conference on Multimedia,pp. 357-360,2007
20. N. Dalal, B. Triggs, and C. Schmid, "Human Detection UsingOriented Histograms of Flow and Appearance," Proc.European Con! Computer Vision, pp. 428-441, 2006
21. C. Schuldt, 1. Laptev, and B. Caputo, "Recognizing HumanActions: A Local SVM Approach, " Proc. Int. Conference onPattern Recognition, pp. 32-36, 2004
22. M. D. Rodriguez, l Ahmed, and M. Shah, "Action Mach: ASpatio-temporal Maximum Average Correlation Height Filterfor Action Recognition, "Proc. IEEE Conl Computer Visionand Pattern Recognition, pp.I-8, 2008
23. T Lan, Y Wang, and G Mori, "Discriminative Figure-CentricModels for Joint Action Localization and Recognition," InProc. Int. Conference on Computer Vision, pp.2003-2010, 2011
24. K. K. Reddy, l Liu, and M. Shah, "Incremental ActionRecognition Using Feature-tree," In Proc. Int. Conference onComputer Vision, pp.1010-1017, 2009
25. J. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld,"Learning Realistic Human Actions from Movies," Proc.IEEE Conl Computer Vision and Pattern Recognition,pp.I-8,2008
26. H. Wang, M. M. Ullah, A Klaser, 1. Laptev, and C. Schmid,"Evaluation of Local Spatio-temporal Features for ActionRecognition," Proc. British Machine Vision Conference,2009
27. S. O'Hara and B.A Draper, "Scalable Action Recognitionwith A Subspace Forest," Proc. IEEE Conl Computer Visionand Pattern Recognition, pp.1210-1217, 2012.