Sparsity-inducing dictionaries for effective action classification. (November 2016)

• Record Type: Journal Article
• Authors: Roy, Debaditya; Srinivas, M.; Krishna Mohan, C.
• Is Part Of: Pattern recognition. Volume 59(2016:Nov.)
• Page Start: 55
• Page End: 62
• Publication Date: 2016-11
• Subjects: Action Classification -- Dictionary Learning -- Sparse Representation -- Action Bank features; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.03.011
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Action recognition in unconstrained videos is one of the most important challenges in computer vision. In this paper, we propose sparsity-inducing dictionaries as an effective representation for action classification in videos. We demonstrate that features obtained from sparsity based representation provide discriminative information useful for classification of action videos into various action classes. We show that the constructed dictionaries are distinct for a large number of action classes resulting in a significant improvement in classification accuracy on the HMDB51 dataset. We further demonstrate the efficacy of dictionaries and sparsity based classification on other large action video datasets like UCF50. Abstract : Highlights: Sparsity-inducing dictionaries as an effective representation for action classification in videos. Features obtained from sparsity based representation provide enough discriminative information for classification of action videos. Constructed dictionaries are distinct for a large number of action classes resulting in a significant improvement in classification accuracy.