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

arXiv: https://arxiv.org/abs/2010.10864 · HTML: https://mlsanity.com/paper/2010.10864/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 30 of 92)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [Revisiting the "Video" in Video-Language Understanding](https://mlsanity.com/paper/2206.01720/) (2022)
- [Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks](https://mlsanity.com/paper/2112.01522/) (2021)
- [FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation](https://mlsanity.com/paper/2311.01813/) (2023)
- [MDMMT: Multidomain Multimodal Transformer for Video Retrieval](https://mlsanity.com/paper/2103.10699/) (2021)
- [ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation](https://mlsanity.com/paper/2406.18522/) (2024)
- [Denoised MDPs: Learning World Models Better Than the World Itself](https://mlsanity.com/paper/2206.15477/) (2022)
- [Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation](https://mlsanity.com/paper/2309.03549/) (2023)
- [Retrospectives on the Embodied AI Workshop](https://mlsanity.com/paper/2210.06849/) (2022)
- [An Unbiased Look at Datasets for Visuo-Motor Pre-Training](https://mlsanity.com/paper/2310.09289/) (2023)
- [Multiview Pseudo-Labeling for Semi-supervised Learning from Video](https://mlsanity.com/paper/2104.00682/) (2021)
- [Scaling 4D Representations](https://mlsanity.com/paper/2412.15212/) (2024)
- [Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision](https://mlsanity.com/paper/2407.06189/) (2024)
- [Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss](https://mlsanity.com/paper/2107.07695/) (2021)
- [DSI-Bench: A Benchmark for Dynamic Spatial Intelligence](https://mlsanity.com/paper/2510.18873/) (2025)
- [Learning high-level visual representations from a child's perspective without strong inductive biases](https://mlsanity.com/paper/2305.15372/) (2023)
- [Multimodal Conversational AI: A Survey of Datasets and Approaches](https://mlsanity.com/paper/2205.06907/) (2022)
- [Gate-Shift-Fuse for Video Action Recognition](https://mlsanity.com/paper/2203.08897/) (2022)
- [SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos](https://mlsanity.com/paper/2404.04565/) (2024)
- [ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding](https://mlsanity.com/paper/2304.08210/) (2023)
- [The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction](https://mlsanity.com/paper/2204.13340/) (2022)
- [Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task](https://mlsanity.com/paper/2211.05039/) (2022)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Dual-Stream Diffusion Net for Text-to-Video Generation](https://mlsanity.com/paper/2308.08316/) (2023)

## Abstract (arXiv)

We describe the 2020 edition of the DeepMind Kinetics human action dataset, which replenishes and extends the Kinetics-700 dataset. In this new version, there are at least 700 video clips from different YouTube videos for each of the 700 classes. 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 network.