mlsanityData to 7 Oct 2026

Human Action Recognition and Prediction: A Survey

arXiv 1806.11230 ↗First posted 28 Jun 2018cs.CVcited by 226

Not on the map. Why?

Abstract (arXiv)

Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state. Vision-based action recognition and prediction from videos are such tasks, where action recognition is to infer human actions (present state) based upon complete action executions, and action prediction to predict human actions (future state) based upon incomplete action executions. These two tasks have become particularly prevalent topics recently because of their explosively emerging real-world applications, such as visual surveillance, autonomous driving vehicle, entertainment, and video retrieval, etc. Many attempts have been devoted in the last a few decades in order to build a robust and effective framework for action recognition and prediction. In this paper, we survey the complete state-of-the-art techniques in action recognition and prediction. Existing models, popular algorithms, technical difficulties, popular action databases, evaluation protocols, and promising future directions are also provided with systematic discussions.

Key facts. Cited by 226 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 27; 2023: 44; 2024: 66; 2025: 46; 2026: 18.

226 papers.

Sort:

By area:

  1. 2023MovieChat: From Dense Token to Sparse Memory for Long Video Understandingcited by 536
  2. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 185
  3. 2022Diffusion Models for Video Prediction and Infillingcited by 134
  4. 2021Evidential Deep Learning for Open Set Action Recognitioncited by 96
  5. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 95
  6. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  7. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  8. 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimationcited by 64
  9. 2021Visual Semantic Role Labeling for Video Understandingcited by 60
  10. 2021Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learningcited by 53
  11. 2021Forecasting Action through Contact Representations from First Person Videocited by 46
  12. 2022HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensorscited by 46
38 more
  1. 2021AGENT: A Benchmark for Core Psychological Reasoningcited by 42
  2. 2024Core Knowledge Deficits in Multi-Modal Language Modelscited by 38
  3. 2021Predicting the Future from First Person (Egocentric) Vision: A Surveycited by 36
  4. 2024EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understandingcited by 35
  5. 2024ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and Morecited by 33
  6. 2024OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understandingcited by 31
  7. 2022Behavioral Intention Prediction in Driving Scenes: A Surveycited by 30
  8. 2023STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognitioncited by 29
  9. 2023A Review of Deep Learning for Video Captioningcited by 28
  10. 2022A Survey on Video Action Recognition in Sports: Datasets, Methods and Applicationscited by 27
  11. 2022Vision Transformers for Action Recognition: A Surveycited by 25
  12. 2023HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actionscited by 25
  13. 2025A Survey on Human Interaction Motion Generationcited by 25
  14. 2024Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modelingcited by 24
  15. 2021A Survey on Human-aware Robot Navigationcited by 23
  16. 2022OpenTAL: Towards Open Set Temporal Action Localizationcited by 23
  17. 2024Understanding Video Transformers via Universal Concept Discoverycited by 22
  18. 2021Levels of explainable artificial intelligence for human-aligned conversational explanationscited by 21
  19. 2024Networking Systems for Video Anomaly Detection: A Tutorial and Surveycited by 21
  20. 2023SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognitioncited by 20
  21. 2025Challenges and Trends in Egocentric Vision: A Surveycited by 20
  22. 2022Egocentric Video Task Translationcited by 19
  23. 2023Diversifying Spatial-Temporal Perception for Video Domain Generalizationcited by 19
  24. 2024Hypergraph-based Multi-View Action Recognition using Event Camerascited by 19
  25. 2023AutoLabel: CLIP-based framework for Open-set Video Domain Adaptationcited by 18
  26. 2022Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmarkcited by 16
  27. 2023The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptationcited by 16
  28. 2024DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognitioncited by 16
  29. 2024XOV-Action: Towards Generalizable Open-Vocabulary Action Recognitioncited by 15
  30. 2024On the Identification of Temporally Causal Representation with Instantaneous Dependencecited by 15
  31. 2021Video action recognition for lane-change classification and prediction of surrounding vehiclescited by 14
  32. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  33. 2024BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Visioncited by 13
  34. 2021Few-Shot Action Recognition with Compromised Metric via Optimal Transportcited by 12
  35. 2024Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detectioncited by 12
  36. 2025HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptationcited by 12
  37. 2021Sparse Adversarial Video Attacks with Spatial Transformationscited by 11
  38. 2023Gaze-based intention estimation: principles, methodologies, and applications in HRIcited by 11

50 most cited of 226 All 226 (JSON)