Human Activity Recognition for Edge Devices
arXiv:1903.07563
Abstract
Video activity Recognition has recently gained a lot of momentum with the release of massive Kinetics (400 and 600) data. Architectures such as I3D and C3D networks have shown state-of-the-art performances for activity recognition. The one major pitfall with these state-of-the-art networks is that they require a lot of compute. In this paper we explore how we can achieve comparable results to these state-of-the-art networks for devices-on-edge. We primarily explore two architectures - I3D and Temporal Segment Network. We show that comparable results can be achieved using one tenth the memory usage by changing the testing procedure. We also report our results on Resnet architecture as our backbone apart from the original Inception architecture. Specifically, we achieve 84.54\% top-1 accuracy on UCF-101 dataset using only RGB frames.
arXiv comment7 pages, 8 figures
References in corpus (9)
- Distilling the Knowledge in a Neural Network
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Deep Residual Learning for Image Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Rethinking the Inception Architecture for Computer Vision
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Long-term Temporal Convolutions for Action Recognition
- Appearance-and-Relation Networks for Video Classification