Parameterized modeling and recognition of activities
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 120-127
- https://doi.org/10.1109/iccv.1998.710709
Abstract
A framework for modeling and recognition of temporal activities is proposed. The modeling of sets of exemplar activities is achieved by parameterizing their representation in the form of principal components. Recognition of spatio-temporal variants of modeled activities is achieved by parameterizing the search in the space of admissible transformations that the activities can undergo. Experiments on recognition of articulated and deformable object motion from image motion parameters are presented.Keywords
This publication has 12 references indexed in Scilit:
- Space-time gesturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning parameterized models of image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A state-based technique for the summarization and recognition of gesturePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Visually Recognizing Speech Using EigensequencesPublished by Springer Nature ,1997
- Human expression recognition from motion using a radial basis function network architectureIEEE Transactions on Neural Networks, 1996
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996
- Recognition of head gestures using hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- An appearance-based representation of actionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Analyzing and recognizing walking figures in XYTPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Matching motion trajectories using scale-spacePattern Recognition, 1993