Fixed Frame Temporal Pooling

View/ Open
Author(s)
Thornton, John
Main, Linda
Srbic, Andrew
Year published
2012
Metadata
Show full item recordAbstract
Applications of unsupervised learning techniques to action recognition have proved highly competitive in comparison to supervised and hand-crafted approaches, despite not being designed to handle image processing problems. Many of these techniques are either based on biological models of cognition or have responses that correlate to those observed in biological systems. In this study we apply (for the first time) an adaptation of the latest hierarchical temporal memory (HTM) cortical learning algorithms (CLAs) to the problem of action recognition. These HTM algorithms are both unsupervised and represent one of the most ...
View more >Applications of unsupervised learning techniques to action recognition have proved highly competitive in comparison to supervised and hand-crafted approaches, despite not being designed to handle image processing problems. Many of these techniques are either based on biological models of cognition or have responses that correlate to those observed in biological systems. In this study we apply (for the first time) an adaptation of the latest hierarchical temporal memory (HTM) cortical learning algorithms (CLAs) to the problem of action recognition. These HTM algorithms are both unsupervised and represent one of the most complete high-level syntheses available of the current neuroscientific understanding of the functioning of neocortex. Specifically, we extend the latest HTM work on augmented spatial pooling, to produce a fixed frame temporal pooler (FFTP). This pooler is evaluated on the well-known KTH action recognition data set and in comparison with the best performing unsupervised learning algorithm for bag-of-features classification in the area: independent subspace analysis (ISA). Our results show FFTP comes within 2% of ISA's performance and outperforms other comparable techniques on this data set. We take these results to be promising, given the preliminary nature of the research and that the FFTP algorithm is only a partial implementation of the proposed HTM architecture.
View less >
View more >Applications of unsupervised learning techniques to action recognition have proved highly competitive in comparison to supervised and hand-crafted approaches, despite not being designed to handle image processing problems. Many of these techniques are either based on biological models of cognition or have responses that correlate to those observed in biological systems. In this study we apply (for the first time) an adaptation of the latest hierarchical temporal memory (HTM) cortical learning algorithms (CLAs) to the problem of action recognition. These HTM algorithms are both unsupervised and represent one of the most complete high-level syntheses available of the current neuroscientific understanding of the functioning of neocortex. Specifically, we extend the latest HTM work on augmented spatial pooling, to produce a fixed frame temporal pooler (FFTP). This pooler is evaluated on the well-known KTH action recognition data set and in comparison with the best performing unsupervised learning algorithm for bag-of-features classification in the area: independent subspace analysis (ISA). Our results show FFTP comes within 2% of ISA's performance and outperforms other comparable techniques on this data set. We take these results to be promising, given the preliminary nature of the research and that the FFTP algorithm is only a partial implementation of the proposed HTM architecture.
View less >
Conference Title
AI 2012: Advances in Artificial Intelligence
Publisher URI
Copyright Statement
© 2012 Springer Berlin / Heidelberg. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher. The original publication is available at www.springerlink.com
Subject
Artificial Intelligence and Image Processing not elsewhere classified