SlowFast Networks for Video Recognition
Citations Over TimeTop 1% of 2019 papers
Abstract
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art accuracy on major video recognition benchmarks, Kinetics, Charades and AVA. Code has been made available at: https://github.com/facebookresearch/SlowFast.
Related Papers
- → A Closer Look at Spatiotemporal Convolutions for Action Recognition(2018)3,457 cited
- → A Closer Look at Spatiotemporal Convolutions for Action Recognition(2017)215 cited
- → On Optimization of Frame Lengths and Frame Delimiting Patterns for Data Communications using Bifix Approach(2005)1 cited
- The Application and Research of Two-tier CAN Bus Network in Mine Monitoring and Control System(2015)
- Spnning-frame Control System based on VB& PLC(2009)