A spatiotemporal model with visual attention for video classification
arXiv:1707.02069
Abstract
High level understanding of sequential visual input is important for safe and stable autonomy, especially in localization and object detection. While traditional object classification and tracking approaches are specifically designed to handle variations in rotation and scale, current state-of-the-art approaches based on deep learning achieve better performance. This paper focuses on developing a spatiotemporal model to handle videos containing moving objects with rotation and scale changes. Built on models that combine Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to classify sequential data, this work investigates the effectiveness of incorporating attention modules in the CNN stage for video classification. The superiority of the proposed spatiotemporal model is demonstrated on the Moving MNIST dataset augmented with rotation and scaling.
Accepted by Robotics: Science and Systems 2017 Workshop on Articulated Model Tracking
References in corpus (6)
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Deformable Convolutional Networks
- Action Recognition using Visual Attention
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- Recurrent Spatial Transformer Networks
- Inverse Compositional Spatial Transformer Networks