Datasets › AVA

AVA (Atomic Visual Actions)

Introduced by Chunhui Gu et al. in AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions1 Jan 2018 archive 2025-07-28

AVA is a project that provides audiovisual annotations of video for improving our understanding of human activity. Each of the video clips has been exhaustively annotated by human annotators, and together they represent a rich variety of scenes, recording conditions, and expressions of human activity. There are annotations for:

  • Kinetics (AVA-Kinetics) - a crossover between AVA and Kinetics. In order to provide localized action labels on a wider variety of visual scenes, authors provide AVA action labels on videos from Kinetics-700, nearly doubling the number of total annotations, and increasing the number of unique videos by over 500x.
  • Actions (AvA Actions) - the AVA dataset densely annotates 80 atomic visual actions in 430 15-minute movie clips, where actions are localized in space and time, resulting in 1.62M action labels with multiple labels per human occurring frequently.
  • Spoken Activity (AVA ActiveSpeaker, AVA Speech). AVA ActiveSpeaker: associates speaking activity with a visible face, on the AVA v1.0 videos, resulting in 3.65 million frames labeled across ~39K face tracks. AVA Speech densely annotates audio-based speech activity in AVA v1.0 videos, and explicitly labels 3 background noise conditions, resulting in ~46K labeled segments spanning 45 hours of data. Image Source: https://www.researchgate.net/profile/Paolo_Napoletano/publication/309327222/figure/fig1/AS:419620126248965@1477056642346/Sample-images-from-the-Aesthetic-Visual-Analysis-AVA-database-sorted-by-their-aesthetic.png

Benchmarks archive 2025-07-28

All 7 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

papers with a benchmark row: 36 · with a code link: 28 · where Syntology ran a sample: 12 (11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (12 of 36 with a benchmark row: 11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 36 of 36 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 113. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Asymmetric Masked Distillation for Pre-Training Small Foundation Models 0 1 6 Nov 2023 not harvested
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles 4 1 1 Jun 2023 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
End-to-End Spatio-Temporal Action Localisation with Video Transformers 0 3 24 Apr 2023 not harvested
On the Benefits of 3D Pose and Tracking for Human Action Recognition 1 1 3 Apr 2023 not harvested
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking 1 3 29 Mar 2023 official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result
Unmasked Teacher: Towards Training-Efficient Video Foundation Models 1 1 28 Mar 2023 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (3 pointer-only for licence)
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning 4 6 8 Dec 2022 not harvested
InternVideo: General Video Foundation Models via Generative and Discriminative Learning 2 2 6 Dec 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified
Holistic Interaction Transformer Network for Action Detection 1 1 23 Oct 2022 not harvested
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection 2 4 15 Jul 2022 not harvested
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training 9 8 23 Mar 2022 official (archive's flag): 9 ran · 10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (12 pointer-only for licence)
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition 1 1 20 Jan 2022 not harvested
Masked Feature Prediction for Self-Supervised Visual Pre-Training 6 1 16 Dec 2021 not harvested
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection 9 1 2 Dec 2021 not harvested
Object-Region Video Transformers 1 1 13 Oct 2021 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (7 pointer-only for licence)
Towards Long-Form Video Understanding 2 1 21 Jun 2021 official (archive's flag): 18 ran · 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (2 pointer-only for licence)
Relation Modeling in Spatio-Temporal Action Localization 0 2 15 Jun 2021 not harvested
Multiscale Vision Transformers 8 6 22 Apr 2021 community repositories only · 13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified (5 pointer-only for licence)
Pose And Joint-Aware Action Recognition 1 1 16 Oct 2020 not harvested
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization 3 4 14 Jun 2020 official (archive's flag): 12 ran · 17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified (4 pointer-only for licence)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization 5 2 15 Nov 2019 community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (2 pointer-only for licence)
Effective Aesthetics Prediction with Multi-level Spatially Pooled Features 1 1 2 Apr 2019 not harvested
D3D: Distilled 3D Networks for Video Action Recognition 1 1 19 Dec 2018 not harvested
Long-Term Feature Banks for Detailed Video Understanding 4 1 12 Dec 2018 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
SlowFast Networks for Video Recognition 15 8 10 Dec 2018 community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)
Video Action Transformer Network 0 2 6 Dec 2018 not harvested
Attention-based Multi-Patch Aggregation for Image Aesthetic Assessment 1 1 22 Oct 2018 not harvested
Actor-Centric Relation Network 1 1 28 Jul 2018 not harvested
A Better Baseline for AVA 0 2 26 Jul 2018 not harvested
NIMA: Neural Image Assessment 12 1 15 Sep 2017 not harvested
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions 9 1 23 May 2017 not harvested
A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment 0 1 2 Apr 2017 not harvested
Photo Aesthetics Ranking Network with Attributes and Content Adaptation 2 1 6 Jun 2016 not harvested
Composition-Preserving Deep Photo Aesthetics Assessment 2 1 1 Jun 2016 not harvested
Deep Aesthetic Quality Assessment with Semantic Information 0 1 18 Apr 2016 not harvested
Deep Multi-Patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation 0 1 1 Dec 2015 not harvested

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • AVA v2.1
  • AVA-ActiveSpeaker
  • AVA-LAEO
  • AVA-Speech
  • AVA v2.2
  • AVA-Kinetics

6 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections