Spatio-temporal Human-Object Interactions for Action Recognition in Videos
Authors:
- Victor EscorciaVEVictor Escorcia
- Juan Carlos NieblesJNJuan Carlos Niebles
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 508-514
Abstract
We introduce a new method for representing the dynamics of human-object interactions in videos. Previous algorithms tend to focus on modeling the spatial relationships between objects and actors, but ignore the evolving nature of this relationship through time. Our algorithm captures the dynamic nature of human-object interactions by modeling how these patterns evolve with respect to time. Our experiments show that encoding such temporal evolution is crucial for correctly discriminating human actions that involve similar objects and spatial human-object relationships, but only differ on the temporal aspect of the interaction, e.g. answer phone and dial phone We validate our approach on two human activity datasets and show performance improvements over competing state-of-the-art representations.Keywords
This publication has 16 references indexed in Scilit:
- Action bank: A high-level representation of activity in video2012
- A combined pose, object, and feature model for action understanding2012
- Structured Learning of Human Interactions in TV ShowsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Human action recognition by learning bases of action attributes and parts2011
- Recognizing human actions by attributes2011
- Modeling mutual context of object and human pose in human-object interaction activities2010
- Activity recognition using the velocity histories of tracked keypoints2009
- Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition2008
- Leveraging temporal, contextual and ordering constraints for recognizing complex activities in video2007
- Conditional models for contextual human motion recognitionComputer Vision and Image Understanding, 2006