Actom sequence models for efficient action detection
Open Access
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3201-3208
Abstract
We address the problem of detecting actions, such as drinking or opening a door, in hours of challenging video data. We propose a model based on a sequence of atomic action units, termed “actoms”, that are characteristic for the action. Our model represents the temporal structure of actions as a sequence of histograms of actom-anchored visual features. Our representation, which can be seen as a temporally structured extension of the bag-of-features, is flexible, sparse and discriminative. We refer to our model as Actom Sequence Model (ASM). Training requires the annotation of actoms for action clips. At test time, actoms are detected automatically, based on a non parametric model of the distribution of actoms, which also acts as a prior on an action's temporal structure. We present experimental results on two recent benchmarks for temporal action detection, “Coffee and Cigarettes” and the dataset of. We show that our ASM method outperforms the current state of the art in temporal action detection.Keywords
This publication has 18 references indexed in Scilit:
- Action unit detection with segment-based SVMs2010
- Learning realistic human actions from movies2008
- Classification using intersection kernel support vector machines is efficient2008
- Action snippets: How many frames does human action recognition require?2008
- A note on Platt’s probabilistic outputs for support vector machinesMachine Learning, 2007
- Leveraging temporal, contextual and ordering constraints for recognizing complex activities in video2007
- Retrieving actions in movies2007
- Discriminative Subsequence Mining for Action Classification2007
- Recognizing human actions: a local SVM approach2004
- Statistical Properties and Adaptive Tuning of Support Vector MachinesMachine Learning, 2002