SlowFast Networks for Video Recognition

Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He
12/10/2018
cs.CV

Official code: facebookresearch/SlowFast (7,436 stars, Apache-2.0, last commit 2026-03-16).

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

View on arXivView PDF

Code Implementations(1)

facebookresearch/SlowFastOfficial100%
Apache-2.0

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

7,4361,296Shell, PythonAug 20, 20197 months agoApache-2.0

Similar Papers

Temporal Segment Networks for Action Recognition in Videos

88% match2 repos1.6k2017

TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device

88% match1 repo2.2k2021

Flatten: Video Action Recognition is an Image Classification task

87% match2024

No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding

87% match1 repo322024

GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition

87% match1 repo122024

Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

86% match2 repos1.6k2016

Cite this paper

@article{feichtenhofer2018slowfast,
  title  = {SlowFast Networks for Video Recognition},
  author = {Christoph Feichtenhofer and Haoqi Fan and Jitendra Malik and Kaiming He},
  year   = {2018},
  eprint = {1812.03982},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1812.03982}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1812.03982.svg)](https://codeofpaper.com/paper/1812.03982)

Discussion