Wta Hash-Based Multimodal Feature Fusion For 3D Human Action Recognition
Keywords
hashing; human action recognition; multimodal feature fusion
Abstract
With the prevalence of the commodity depth sensors (e.g. Kinect), multimodal data including RGB stream, depth stream and audio stream have been utilized in various applications such as video games, education and health. Nevertheless, it is still very challenging to effectively fuse the features from multimodal data. In this paper, we propose a WTA (Winner-Take-All) Hash-based feature fusion algorithm and investigate its application in 3D human action recognition. Specifically, the WTA Hashing is performed to encode features from different modalities into the ordinal space. By leveraging the ordinal measures rather than using the absolute value of the original features, such feature embedding can provide a form of resilience to the scale and numerical perturbations. We propose a frame-level feature fusion algorithm and develop a WTA Hash-embedded warping algorithm to measure the similarity between two sequences. Experiments performed on three public 3D human action datasets show that the proposed fusion algorithm has achieved state-of-the-art recognition results even with the nearest neighbor search.
Publication Date
3-25-2016
Publication Title
Proceedings - 2015 IEEE International Symposium on Multimedia, ISM 2015
Number of Pages
184-190
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ISM.2015.11
Copyright Status
Unknown
Socpus ID
84969651365 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84969651365
STARS Citation
Ye, Jun; Li, Kai; and Hua, Kien A., "Wta Hash-Based Multimodal Feature Fusion For 3D Human Action Recognition" (2016). Scopus Export 2015-2019. 4309.
https://stars.library.ucf.edu/scopus2015/4309