Action Recognition Based on Discriminative Embedding of Actions Using Siamese Networks

Roy, Debaditya and C, Krishna Mohan and Kodukula, Sri Rama Murty (2018) Action Recognition Based on Discriminative Embedding of Actions Using Siamese Networks. In: 25th IEEE International Conference on Image Processing (ICIP), 7-10 October 2018, Athens, Greece.

Full text not available from this repository. (Request a copy)

Abstract

Actions can be recognized effectively when the various atomic attributes forming the action are identified and combined in the form of a representation. In this paper, a low-dimensional representation is extracted from a pool of attributes learned in a universal Gaussian mixture model using factor analysis. However, such a representation cannot adequately discriminate between actions with similar attributes. Hence, we propose to classify such actions by leveraging the corresponding class labels. We train a Siamese deep neural network with a contrastive loss on the low-dimensional representation. We show that Siamese networks allow effective discrimination even between similar actions. The efficacy of the proposed approach is demonstrated on two benchmark action datasets, HMDB51 and MPII Cooking Activities. On both the datasets, the proposed method improves the state-of-the-art performance considerably.

[error in script]

IITH Creators: