The AVA-Kinetics Localized Human Actions Video Dataset

Abstract

This paper describes the AVA-Kinetics localized human actions video dataset. The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these new AVA annotated Kinetics clips. The dataset contains over 230k clips annotated with the 80 AVA action classes for each of the humans in key-frames. We describe the annotation process and provide statistics about the new dataset. We also include a baseline evaluation using the Video Action Transformer Network on the AVA-Kinetics dataset, demonstrating improved performance for action classification on the AVA test set. The dataset can be downloaded from https://research.google.com/ava/

8 pages, 8 figures

References in corpus (2)

• The Kinetics Human Action Video Dataset
• A Short Note on the Kinetics-700-2020 Human Action Dataset

Cited by in corpus (16)

• A Short Note on the Kinetics-700-2020 Human Action Dataset
• Self-Supervised Learning for Videos: A Survey
• A Comprehensive Study of Deep Video Action Recognition
• Measurement in AI Policy: Opportunities and Challenges
• Semi-TCL: Semi-Supervised Track Contrastive Representation Learning
• Video Action Understanding
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis
• Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
• HighlightMe: Detecting Highlights from Human-Centric Videos
• Relation Modeling in Spatio-Temporal Action Localization
• MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
• 1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
• Spatial-Temporal Alignment Network for Action Recognition and Detection
• From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video
• Learning Goals from Failure