A Short Note on the Kinetics-700 Human Action Dataset

07/15/2019
by   Joao Carreira, et al.
1

We describe an extension of the DeepMind Kinetics human action dataset from 600 classes to 700 classes, where for each class there are at least 600 video clips from different YouTube videos. This paper details the changes introduced for this new release of the dataset, and includes a comprehensive set of statistics as well as baseline results using the I3D neural network architecture.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2020

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

We describe the 2020 edition of the DeepMind Kinetics human action datas...
research
08/03/2018

A Short Note about Kinetics-600

We describe an extension of the DeepMind Kinetics human action dataset f...
research
05/19/2017

The Kinetics Human Action Video Dataset

We describe the DeepMind Kinetics human action video dataset. The datase...
research
08/15/2023

Action Class Relation Detection and Classification Across Multiple Video Datasets

The Meta Video Dataset (MetaVD) provides annotated relations between act...
research
11/25/2019

Oops! Predicting Unintentional Action in Video

From just a short glance at a video, we can often tell whether a person'...
research
04/30/2019

Attentive Spatio-Temporal Representation Learning for Diving Classification

Competitive diving is a well recognized aquatic sport in which a person ...
research
04/05/2018

The diveXplore System at the Video Browser Showdown 2018 - Final Notes

This short paper provides further details of the diveXplore system (form...

Please sign up or login with your details

Forgot password? Click here to reset