Fully-Coupled Two-Stream Spatiotemporal Networks For Extremely Low Resolution Action Recognition
Abstract
A major emerging challenge is how to protect people's privacy as cameras and computer vision are increasingly integrated into our daily lives, including in smart devices inside homes. A potential solution is to capture and record just the minimum amount of information needed to perform a task of interest. In this paper, we propose a fully-coupled two-stream spatiotemporal architecture for reliable human action recognition on extremely low resolution (e.g., 1216 pixel) videos. We provide an efficient method to extract spatial and temporal features and to aggregate them into a robust feature representation for an entire action video sequence. We also consider how to incorporate high resolution videos during training in order to build better low resolution action recognition models. We evaluate on two publicly-available datasets, showing significant improvements over the state-of-the-art.
Publication Date
5-3-2018
Publication Title
Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018
Volume
2018-January
Number of Pages
1607-1615
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/WACV.2018.00178
Copyright Status
Unknown
Socpus ID
85050960082 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85050960082
STARS Citation
Xu, Mingze; Sharghi, Aidean; Chen, Xin; and Crandall, David J., "Fully-Coupled Two-Stream Spatiotemporal Networks For Extremely Low Resolution Action Recognition" (2018). Scopus Export 2015-2019. 8959.
https://stars.library.ucf.edu/scopus2015/8959