# AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions

arXiv: https://arxiv.org/abs/1705.08421 · HTML: https://mlsanity.com/paper/1705.08421/

## Key facts

- Cited by 449 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2017.

## Built on by (most cited first, 30 of 449)

- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action](https://mlsanity.com/paper/2312.17172/) (2023)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling](https://mlsanity.com/paper/2207.02595/) (2022)
- [Towards Long-Form Video Understanding](https://mlsanity.com/paper/2106.11310/) (2021)
- [Tarsier: Recipes for Training and Evaluating Large Video Description Models](https://mlsanity.com/paper/2407.00634/) (2024)
- [EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations](https://mlsanity.com/paper/2209.13064/) (2022)

## Abstract (arXiv)

This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute video clips; (4) people temporally linked across consecutive segments; and (5) using movies to gather a varied set of action representations. This departs from existing datasets for spatio-temporal action recognition, which typically provide sparse annotations for composite actions in short video clips. We will release the dataset publicly. AVA, with its realistic scene and action complexity, exposes the intrinsic difficulty of action recognition. To benchmark this, we present a novel approach for action localization that builds upon the current state-of-the-art methods, and demonstrates better performance on JHMDB and UCF101-24 categories. While setting a new state of the art on existing datasets, the overall results on AVA are low at 15.6% mAP, underscoring the need for developing new approaches for video understanding.