24 December 2013 Clustering space-time interest points for action representation
Author Affiliations +
Proceedings Volume 9067, Sixth International Conference on Machine Vision (ICMV 2013); 90671G (2013) https://doi.org/10.1117/12.2051581
Event: Sixth International Conference on Machine Vision (ICMV 13), 2013, London, United Kingdom
This paper presents a novel approach to represent human actions in a video. Our approach deals with the limitation of local representation, i.e. space-time interest points, which cannot adequately represent actions in a video due to lack of global information about geometric relationships among interest points. It adds the geometric relationships to interest points by clustering interest points using squared Euclidean distances, followed by using a minimum hexahedron to represent each cluster. Within each video, we build a multi-dimensional histogram based on the characteristics of hexahedrons in the video for recognition. The experimental results show that the proposed representation is powerful to include the global information on top of local interest points and it successfully increases the accuracy of action recognition.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sou-Young Jin, Sou-Young Jin, Ho-Jin Choi, Ho-Jin Choi, "Clustering space-time interest points for action representation", Proc. SPIE 9067, Sixth International Conference on Machine Vision (ICMV 2013), 90671G (24 December 2013); doi: 10.1117/12.2051581; https://doi.org/10.1117/12.2051581


Back to Top