The Kinetics Human Action Video Dataset
Will Kay, Joao Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier,, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul, Natsev, Mustafa Suleyman, Andrew Zisserman

TL;DR
The Kinetics dataset is a large, diverse collection of human action videos from YouTube, designed to facilitate research in action recognition with baseline benchmarks and bias analysis.
Contribution
This paper introduces the Kinetics dataset, a comprehensive and diverse human action video dataset with baseline results and bias analysis.
Findings
Dataset contains 400 action classes with at least 400 clips each.
Baseline neural network performance figures are provided.
Preliminary bias analysis related to dataset imbalance.
Abstract
We describe the DeepMind Kinetics human action video dataset. The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions are human focussed and cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands. We describe the statistics of the dataset, how it was collected, and give some baseline performance figures for neural network architectures trained and tested for human action classification on this dataset. We also carry out a preliminary analysis of whether imbalance in the dataset leads to bias in the classifiers.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Anomaly Detection Techniques and Applications · Video Surveillance and Tracking Methods
