Multiple/Single-View Human Action Recognition via Part-Induced Multitask Structural Learning

doi:10.1109/TCYB.2014.2347057

Return

Multiple/Single-View Human Action Recognition via Part-Induced Multitask Structural Learning

2015-06-01

PRE

DOI：10.1109/TCYB.2014.2347057

Original

Original request for help

Save

Abstract

En 中文

This paper proposes a unified framework for multiple/single-view human action recognition. First, we propose the hierarchical partwise bag-of-words representation which encodes both local and global visual saliency based on the body structure cue. Then, we formulate the multiple/single-view human action recognition as a part-regularized multitask structural learning (MTSL) problem which has two advantages on both model learning and feature selection: 1) preserving the consistence between the body-based action classification and the part-based action classification with the complementary information among different action categories and multiple views and 2) discovering both action-specific and action-shared feature sub-spaces to strengthen the generalization ability of model learning. Moreover, we contribute two novel human action recognition datasets, TJU (a single-view multimodal dataset) and MV-TJU (a multiview multimodal dataset). The proposed method is validated on three kinds of challenging datasets, including two single-view RGB datasets (KTH and TJU), two well-known depth dataset (MSR action 3-D and MSR daily activity 3-D), and one novel multiview multimodal dataset (MV-TJU). The extensive experimental results show that this method can outperform the popular 2-D/3-D part model-based methods and several other competing methods for multiple/single-view human action recognition in both RGB and depth modalities. To our knowledge, this paper is the first to demonstrate the applicability of MTSL with part-based regularization on multiple/single-view human action recognition in both RGB and depth modalities.

Keywords:

Multitask learning (MTL)

multiview human action recognition

partwise bag-of-words

structural learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.