Human Action Recognition by Semilatent Topic Models
- 20 February 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ieee Transactions On Pattern Analysis and Machine Intelligence
- Vol. 31 (10), 1762-1774
- https://doi.org/10.1109/tpami.2009.43
Abstract
We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word". Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets.Keywords
This publication has 40 references indexed in Scilit:
- Action recognition by learning mid-level motion featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- A Hierarchical Model of Shape and Appearance for Human Action ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Retrieving actions in moviesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Discriminative Subsequence Mining for Action ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Behavior Recognition via Sparse Spatio-Temporal FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Conditional models for contextual human motion recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Actions as space-time shapesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Efficient visual event detection using volumetric featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Recognizing human actions: a local SVM approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Space-time interest pointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003