Action recognition using exemplar-based embedding
- 1 June 2008
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
In this paper, we address the problem of representing human actions using visual cues for the purpose of learning and recognition. Traditional approaches model actions as space-time representations which explicitly or implicitly encode the dynamics of an action through temporal dependencies. In contrast, we propose a new compact and efficient representation which does not account for such dependencies. Instead, motion sequences are represented with respect to a set of discriminative static key-pose exemplars and without modeling any temporal ordering. The interest is a time-invariant representation that drastically simplifies learning and recognition by removing time related information such as speed or length of an action. The proposed representation is equivalent to embedding actions into a space defined by distances to key-pose exemplars. We show how to build such embedding spaces of low dimension by identifying a vocabulary of highly discriminative exemplars using a forward selection. To test our representation, we have used a publicly available dataset which demonstrates that our method can precisely recognize actions, even with cluttered and non-segmented sequences.Keywords
This publication has 20 references indexed in Scilit:
- A 3-dimensional sift descriptor and its application to action recognitionPublished by Association for Computing Machinery (ACM) ,2007
- Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A Hierarchical Model of Shape and Appearance for Human Action ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- PEET: Prototype Embedding and Embedding Transition for Matching Vehicles over Disparate ViewpointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A Biologically Inspired System for Action RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Recognizing human actions: a local SVM approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Probabilistic tracking in a metric spacePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- 10.1162/153244303322753616Applied Physics Letters, 2000
- Wrappers for feature subset selectionArtificial Intelligence, 1997
- Visual perception of biological motion and a model for its analysisPerception & Psychophysics, 1973