Max‐margin discriminative random fields for multimodal human action recognition. Issue 12 (1st June 2014)

• Record Type: Journal Article
• Authors: Su, Yuting; Ma, Li; Liu, An‐An; Yang, Zhaoxuan
• Is Part Of: Electronics letters. Volume 50:Issue 12(2014)
• Page Start: 870
• Page End: 872
• Publication Date: 2014-06-01
• Subjects: learning (artificial intelligence) -- image motion analysis -- gesture recognition; max‐margin discriminative random field model -- multimodal human action recognition -- multiple modalities -- joint modelling -- parallel sequential observations -- hidden‐state layers -- model formulation -- model learning -- max‐margin learning method -- latent correlation; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2014.1027
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : Proposed is a max‐margin discriminative random fields model for multimodal human action recognition. To incorporate multiple modalities for joint modelling, a specific graphical structure with parallel sequential observations and related hidden‐state layers is designed. Moreover, the corresponding potential functions for model formulation are designed. For model learning, the max‐margin learning method is proposed to discover both latent correlation among multimodal data and temporal context within individual modality. A comparison experiment shows that the proposed model can boost the performance of human action recognition by taking advantage of complementary characteristics from multiple modalities.