mlsanityData to 7 Oct 2026

The AVA-Kinetics Localized Human Actions Video Dataset

arXiv 2005.00214 ↗First posted 1 May 2020cs.CV cs.LG eess.IVcited by 82

Not on the map. Why?

Abstract (arXiv)

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/

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 17; 2023: 18; 2024: 17; 2025: 12; 2026: 4.

82 papers.

Sort:

By area:

  1. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 516
  2. 2022InternVideo: General Video Foundation Models via Generative and Discriminative Learningcited by 441
  3. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  4. 2022EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relationscited by 139
  5. 2024VideoPrism: A Foundational Visual Encoder for Video Understandingcited by 103
  6. 2022Self-Supervised Learning for Videos: A Surveycited by 85
  7. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 82
  8. 2021Visual Semantic Role Labeling for Video Understandingcited by 60
  9. 2021FineAction: A Fine-Grained Video Dataset for Temporal Action Localizationcited by 60
  10. 2024Pixel-Wise Recognition for Holistic Surgical Scene Understandingcited by 48
  11. 2024Foundation Models for Video Understanding: A Surveycited by 46
  12. 2022Spotting Temporally Precise, Fine-Grained Events in Videocited by 40
38 more
  1. 2021JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detectioncited by 38
  2. 2023On the Benefits of 3D Pose and Tracking for Human Action Recognitioncited by 32
  3. 2024Masked Image Modeling: A Surveycited by 28
  4. 2022A Survey on Video Action Recognition in Sports: Datasets, Methods and Applicationscited by 27
  5. 2021Semi-TCL: Semi-Supervised Track Contrastive Representation Learningcited by 23
  6. 2023Accurate and Fast Compressed Video Captioningcited by 21
  7. 2023End-to-End Spatio-Temporal Action Localisation with Video Transformerscited by 20
  8. 2024What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interactioncited by 18
  9. 2025Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Markscited by 17
  10. 2021Contextualized Spatio-Temporal Contrastive Learning with Self-Supervisioncited by 15
  11. 2023VideoGLUE: Video General Understanding Evaluation of Foundation Modelscited by 14
  12. 2024SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videoscited by 14
  13. 2024BaboonLand Dataset: Tracking Primates in the Wild and Automating Behaviour Recognition from Drone Videoscited by 14
  14. 2024Common Ground Tracking in Multimodal Dialoguecited by 13
  15. 2021Discrete neural representations for explainable anomaly detectioncited by 12
  16. 2022Movies2Scenes: Using Movie Metadata to Learn Scene Representationcited by 11
  17. 2021X-MAN: Explaining multiple sources of anomalies in videocited by 10
  18. 2023What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructionscited by 10
  19. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  20. 2025TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialoguescited by 9
  21. 20223MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videoscited by 8
  22. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  23. 2022Beyond Transfer Learning: Co-finetuning for Action Localisationcited by 8
  24. 2022A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detectorcited by 6
  25. 2021Relation Modeling in Spatio-Temporal Action Localizationcited by 5
  26. 2021Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tenniscited by 5
  27. 2021Exploring Temporal Granularity in Self-Supervised Video Representation Learningcited by 5
  28. 2023SCB-Dataset3: A Benchmark for Detecting Student Classroom Behaviorcited by 5
  29. 2024Conformance Checking of Fuzzy Logs against Declarative Temporal Specificationscited by 5
  30. 2022Fine-grained Activities of People Worldwidecited by 4
  31. 2022Baby Physical Safety Monitoring in Smart Home Using Action Recognition Systemcited by 4
  32. 2023Towards Activated Muscle Group Estimation in the Wildcited by 4
  33. 2023Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localizationcited by 4
  34. 2025Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videoscited by 4
  35. 2025From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approachcited by 4
  36. 2021HighlightMe: Detecting Highlights from Human-Centric Videoscited by 3
  37. 2023CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detectioncited by 3
  38. 2026Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Modelscited by 3

50 most cited of 82 All 82 (JSON)