Title :
Max-margin discriminative random fields for multimodal human action recognition
Author :
Yuting Su ; Li Ma ; An-An Liu ; Zhaoxuan Yang
Author_Institution :
Dept. of Electron. Eng., Tianjin Univ., Tianjin, China
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.
Keywords :
gesture recognition; image motion analysis; learning (artificial intelligence); hidden-state layers; joint modelling; latent correlation; max-margin discriminative random field model; max-margin learning method; model formulation; model learning; multimodal human action recognition; multiple modalities; parallel sequential observations;
Journal_Title :
Electronics Letters
DOI :
10.1049/el.2014.1027