Publications -> Conference Papers

Zero-Shot Human Activity Recognition via Nonlinear Compatibility Based Method


Authors: W. Wang, C. Miao, and S. Hao
Title: Zero-Shot Human Activity Recognition via Nonlinear Compatibility Based Method
Abstract: Human activity recognition aims to recognize human activities from sensor readings. Most of existing methods in this area can only recognize activities contained in training dataset. However, in practical applications, previously unseen activities are often encountered. In this paper, we propose a new zero-shot learning method to solve the problem of recognizing previously unseen activities. The proposed method learns a nonlinear compatibility function between feature space instances and semantic space prototypes. With this function, testing instances are classified to unseen activities with highest compatibility scores. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on three public datasets. Experimental results show that our proposed method consistently outperforms state-of-the-art methods in human activity recognition problems.
Keywords: 
Conference Name: 2017 IEEE/WIC/ACM International Conference on Web Intelligence (WI'17)
Location: Leipzig, Germany
Publisher: ACM
Year: 2017
Accepted PDF File: Zero-Shot_Human_Activity_Recognition_via_Nonlinear_Compatibility_Based_Method_accepted.pdf
Permanent Link: https://doi.org/10.1145/3106426.3106526
Reference: W. Wang, C. Miao, and S. Hao, “Zero-shot human activity recognition via nonlinear compatibility based method,” in Proceedings of the 2017 IEEE/WIC/ACM International Conference on Web Intelligence (WI’17). ACM, August 2017, pp. 322–330.
bibtex: 
@inproceedings{LILY-c131, 
    author = {Wang, Wei and Miao, Chunyan and Hao, Shuji},
    title  = {Zero-Shot Human Activity Recognition via Nonlinear Compatibility Based Method},  
    booktitle = {Proceedings of the 2017 IEEE/WIC/ACM International Conference on Web Intelligence (WI'17)}, 
    year  = {2017}, 
    month = {August}, 
    pages = {322-330}, 
    location = {Leipzig, Germany},
    publisher = {ACM},
 }