Semi-coupled two-stream fusion ConvNets for action recognition at extremely low resolutions
MetadataShow full item record
Citation (published version)Jiawei Chen, Jonathan Wu, Janusz Konrad, Prakash Ishwar. 2017. "Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions." 2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017). 17th IEEE Winter Conference on Applications of Computer Vision (WACV). Santa Rosa, CA, 2017-03-24 - 2017-03-31. https://doi.org/10.1109/WACV.2017.23
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such as private homes, hospitals, nursing/rehabilitation facilities, etc. In this paper, we propose a semi-coupled, filter-sharing network that leverages high-resolution (HR) videos during training in order to assist an eLR ConvNet. We also study methods for fusing spatial and temporal ConvNets customized for eLR videos in order to take advantage of appearance and motion information. Our method outperforms state-of-the-art methods at extremely low resolutions on IXMAS (93:7%) and HMDB (29:2%) datasets.