mlsanityData to 7 Oct 2026

VideoGraph: Recognizing Minutes-Long Human Activities in Videos

arXiv 1905.05143 ↗First posted 13 May 2019cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Many human activities take minutes to unfold. To represent them, related works opt for statistical pooling, which neglects the temporal structure. Others opt for convolutional methods, as CNN and Non-Local. While successful in learning temporal concepts, they are short of modeling minutes-long temporal dependencies. We propose VideoGraph, a method to achieve the best of two worlds: represent minutes-long human activities and learn their underlying temporal structure. VideoGraph learns a graph-based representation for human activities. The graph, its nodes and edges are learned entirely from video datasets, making VideoGraph applicable to problems without node-level annotation. The result is improvements over related works on benchmarks: Epic-Kitchen and Breakfast. Besides, we demonstrate that VideoGraph is able to learn the temporal structure of human activities in minutes-long videos.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 10; 2024: 15; 2025: 11; 2026: 3.

57 papers.

Sort:

By area:

  1. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  2. 2024VideoAgent: Long-form Video Understanding with Large Language Model as Agentcited by 323
  3. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 223
  4. 2023A Simple LLM Framework for Long-Range Video Question-Answeringcited by 176
  5. 2022Long Movie Clip Classification with State-Space Video Modelscited by 106
  6. 2023Selective Structured State-Spaces for Long-Form Video Understandingcited by 105
  7. 2022Learning To Recognize Procedural Activities with Distant Supervisioncited by 85
  8. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  9. 2023AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?cited by 79
  10. 2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 63
  11. 2024DrVideo: Document Retrieval Based Long Video Understandingcited by 63
  12. 2022Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videoscited by 50
38 more
  1. 2021Activity Graph Transformer for Temporal Action Localizationcited by 48
  2. 2024AMEGO: Active Memory from long EGOcentric videoscited by 35
  3. 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understandingcited by 30
  4. 2022Rethinking Learning Approaches for Long-Term Action Anticipationcited by 29
  5. 2024VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMscited by 29
  6. 2021Coarse to Fine Multi-Resolution Temporal Convolutional Networkcited by 28
  7. 2023PALM: Predicting Actions through Language Modelscited by 28
  8. 2021Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activitiescited by 26
  9. 2021No frame left behind: Full Video Action Recognitioncited by 24
  10. 2022C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentationcited by 23
  11. 2024Video Token Merging for Long-form Video Understandingcited by 22
  12. 2025HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understandingcited by 17
  13. 2025BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimationcited by 17
  14. 2022Gate-Shift-Fuse for Video Action Recognitioncited by 15
  15. 2021Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognitioncited by 14
  16. 2022Turbo Training with Token Dropoutcited by 14
  17. 2024Enhancing Long Video Understanding via Hierarchical Event-Based Memorycited by 14
  18. 2022Concept Graph Neural Networks for Surgical Video Understandingcited by 13
  19. 2023Chop & Learn: Recognizing and Generating Object-State Compositionscited by 13
  20. 2023United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videoscited by 13
  21. 2021Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videoscited by 11
  22. 2024IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videoscited by 11
  23. 2025Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipationcited by 10
  24. 2023DiffAnt: Diffusion Models for Action Anticipationcited by 9
  25. 2021PGT: A Progressive Method for Training Models on Long Videoscited by 7
  26. 2023Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understandingcited by 7
  27. 2024AdaCM2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reductioncited by 7
  28. 2023Are current long-term video understanding datasets long-term?cited by 6
  29. 2024Towards Long Video Understanding via Fine-detailed Video Story Generationcited by 6
  30. 2024Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intentioncited by 5
  31. 2025Vision and Intention Boost Large Language Model in Long-Term Action Anticipationcited by 5
  32. 2025MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognitioncited by 4
  33. 2024A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videoscited by 3
  34. 2025VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretrainingcited by 3
  35. 2025LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoderscited by 3
  36. 2022SVGraph: Learning Semantic Graphs from Instructional Videoscited by 2
  37. 2023Video BagNet: short temporal receptive fields increase robustness in long-term action recognitioncited by 2
  38. 2025REEF: Relevance-Aware and Efficient LLM Adapter for Video Understandingcited by 2

50 most cited of 57 All 57 (JSON)