Motion Feature Network: Fixed Motion Filter for Action Recognition
arXiv:1807.10037
Abstract
Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in combination with a set of RGB images that contain spatial information has shown great performance enhancement in the action recognition tasks. However, it has an expensive computational cost and requires two-stream (RGB and optical flow) framework. In this paper, we propose MFNet (Motion Feature Network) containing motion blocks which make it possible to encode spatio-temporal information between adjacent frames in a unified network that can be trained end-to-end. The motion block can be attached to any existing CNN-based action recognition frameworks with only a small additional cost. We evaluated our network on two of the action recognition datasets (Jester and Something-Something) and achieved competitive performances for both datasets by training the networks from scratch.
arXiv commentECCV 2018, 14 pages, 6 figures, 4 tables
References in corpus (15)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- The Kinetics Human Action Video Dataset
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- ConvNet Architecture Search for Spatiotemporal Feature Learning
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
- Learnable pooling with Context Gating for video classification
- Hidden Two-Stream Convolutional Networks for Action Recognition
- Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
- Real-time Action Recognition with Enhanced Motion Vector CNNs
- Appearance-and-Relation Networks for Video Classification
- Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
- Temporal Relational Reasoning in Videos
- Fusing Multi-Stream Deep Networks for Video Classification
- ActionFlowNet: Learning Motion Representation for Action Recognition