mlsanityData to 7 Oct 2026

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

arXiv 2010.10864 ↗First posted 21 Oct 2020cs.CV cs.LGcited by 89

Not on the map. Why?

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.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 23; 2023: 23; 2024: 17; 2025: 11; 2026: 4.

89 papers.

Sort:

By area:

  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  2. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  3. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  4. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  5. 2021Less is More: ClipBERT for Video-and-Language Learning via Sparse Samplingcited by 484
  6. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  7. 2024T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generationcited by 177
  8. 2022Revisiting the "Video" in Video-Language Understandingcited by 167
  9. 2021Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Taskscited by 124
  10. 2023FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generationcited by 119
  11. 2021MDMMT: Multidomain Multimodal Transformer for Video Retrievalcited by 78
  12. 2024ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generationcited by 74
38 more
  1. 2022Denoised MDPs: Learning World Models Better Than the World Itselfcited by 66
  2. 2023Reuse and Diffuse: Iterative Denoising for Text-to-Video Generationcited by 49
  3. 2022Retrospectives on the Embodied AI Workshopcited by 46
  4. 2023An Unbiased Look at Datasets for Visuo-Motor Pre-Trainingcited by 41
  5. 2021Multiview Pseudo-Labeling for Semi-supervised Learning from Videocited by 32
  6. 2024Scaling 4D Representationscited by 30
  7. 2024Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervisioncited by 24
  8. 2021Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Losscited by 23
  9. 2023Learning high-level visual representations from a child's perspective without strong inductive biasescited by 22
  10. 2025DSI-Bench: A Benchmark for Dynamic Spatial Intelligencecited by 20
  11. 2022Multimodal Conversational AI: A Survey of Datasets and Approachescited by 16
  12. 2022Gate-Shift-Fuse for Video Action Recognitioncited by 15
  13. 2023ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understandingcited by 14
  14. 2024SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videoscited by 14
  15. 2022The Wisdom of Crowds: Temporal Progressive Attention for Early Action Predictioncited by 13
  16. 2022Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Surveycited by 12
  17. 2023Dual-Stream Diffusion Net for Text-to-Video Generationcited by 12
  18. 2022Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Taskcited by 11
  19. 2023Learning from One Continuous Video Streamcited by 11
  20. 2024OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videoscited by 10
  21. 2022Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonizationcited by 9
  22. 2021Zero-Shot Action Recognition from Diverse Object-Scene Compositionscited by 8
  23. 2023ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videoscited by 8
  24. 2024DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognitioncited by 8
  25. 2024Contextual Emotion Recognition using Large Vision Language Modelscited by 8
  26. 2024EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videoscited by 8
  27. 2024Human Action Anticipation: A Surveycited by 8
  28. 2025HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMscited by 8
  29. 2022Surgical Workflow Recognition: from Analysis of Challenges to Architectural Studycited by 6
  30. 2024Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Reviewcited by 6
  31. 2024Self-supervised learning of video representations from a child's perspectivecited by 6
  32. 2021Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tenniscited by 5
  33. 2022Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Modelcited by 5
  34. 2025Dynamic Reflections: Probing Video Representations with Text Alignmentcited by 5
  35. 2021TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videoscited by 4
  36. 2021How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?cited by 4
  37. 2022HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignmentcited by 4
  38. 2023Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shiftscited by 4

50 most cited of 89 All 89 (JSON)