Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
This addresses privacy concerns in environments like homes and hospitals by enabling reliable action recognition with low-resolution cameras, though it is incremental as it builds on existing ConvNet methods.
The paper tackled action recognition at extremely low resolutions (e.g., 16x12 pixels) by proposing a semi-coupled filter-sharing network that leverages high-resolution videos during training and fuses spatial and temporal ConvNets, achieving 93.7% on IXMAS and 29.2% on HMDB datasets.
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.