Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
arXiv:1610.03898
Abstract
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 x 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.
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Two-Stream Convolutional Networks for Action Recognition in Videos
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Studying Very Low Resolution Recognition Using Deep Networks
- Deeply Coupled Auto-encoder Networks for Cross-view Classification