Please use this identifier to cite or link to this item:
|Title:||Middle-level representation for human activities recognition : the role of spatio-temporal relationships||Authors:||Yuan, Fei
|Keywords:||DRNTU::Engineering::Electrical and electronic engineering||Issue Date:||2012||Publisher:||Springer Berlin Heidelberg||Source:||Yuan, F., Prinet, V., & Yuan, J. (2012). Middle-Level Representation for Human Activities Recognition: The Role of Spatio-Temporal Relationships. In K.N. Kutulakos (Ed.), Trends and Topics in Computer Vision, ECCV 2010 Workshops, Part I, LNCS 6553, (pp.168–180). Springer-Verlag Berlin Heidelberg.||Abstract:||We tackle the challenging problem of human activity recognition in realistic video sequences. Unlike local features-based methods or global template-based methods, we propose to represent a video sequence by a set of middle-level parts. A part, or component, has consistent spatial structure and consistent motion. We first segment the visual motion patterns and generate a set of middle-level components by clustering keypoints-based trajectories extracted from the video. To further exploit the interdependencies of the moving parts, we then define spatio-temporal relationships between pairwise components. The resulting descriptive middle-level components and pairwise-components thereby catch the essential motion characteristics of human activities. They also give a very compact representation of the video. We apply our framework on popular and challenging video datasets: Weizmann dataset and UT-Interaction dataset. We demonstrate experimentally that our middle-level representation combined with a χ 2-SVM classifier equals to or outperforms the state-of-the-art results on these dataset.||URI:||https://hdl.handle.net/10356/103853
|ISBN:||978-3-642-35748-0; 978-3-642-35749-7||DOI:||10.1007/978-3-642-35749-7||Rights:||© 2012 Springer-Verlag Berlin Heidelberg.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Books & Book Chapters|
Files in This Item:
|Middle-Level Representation for Human Activities Recognition_the Role of Spatio-temporal Relationships.pdf||1.28 MB||Adobe PDF|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.