mlsanityData to 7 Oct 2026

Recurrent Models of Visual Attention

arXiv 1406.6247 ↗First posted 24 Jun 2014cs.LG cs.CV stat.MLcited by 344

Not on the map. Why?

Abstract (arXiv)

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image size. While the model is non-differentiable, it can be trained using reinforcement learning methods to learn task-specific policies. We evaluate our model on several image classification tasks, where it significantly outperforms a convolutional neural network baseline on cluttered images, and on a dynamic visual control problem, where it learns to track a simple object without an explicit training signal for doing so.

Key facts. Cited by 344 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jun 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 104; 2022: 81; 2023: 65; 2024: 41; 2025: 27; 2026: 26.

344 papers.

Sort:

By area:

  1. 2021Dynamic Neural Networks: A Surveycited by 405
  2. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  3. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  4. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  5. 2022Visual Attention Networkcited by 210
  6. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  7. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  8. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  9. 2023Consciousness in Artificial Intelligence: Insights from the Science of Consciousnesscited by 99
  10. 2023System 2 Attention (is something you might need too)cited by 85
  11. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  12. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
38 more
  1. 2021Adaptive Focus for Efficient Video Recognitioncited by 76
  2. 2021Is Attention Better Than Matrix Decomposition?cited by 75
  3. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  4. 2023RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmarkcited by 70
  5. 2021Differentiable Patch Selection for Image Recognitioncited by 68
  6. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
  7. 2022MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answeringcited by 55
  8. 2023Learning to Maximize Mutual Information for Dynamic Feature Selectioncited by 54
  9. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  10. 2024Toward Visual Grounding: A Surveycited by 52
  11. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  12. 2021DRIVE: Deep Reinforced Accident Anticipation with Visual Explanationcited by 46
  13. 2021Vision Transformer with Progressive Samplingcited by 44
  14. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  15. 2022Rethinking Attention-Model Explainability through Faithfulness Violation Testcited by 43
  16. 2021Semantic Concentration for Domain Adaptationcited by 42
  17. 2024Softmax is not Enough (for Sharp Size Generalisation)cited by 42
  18. 2022Glance and Focus Networks for Dynamic Visual Recognitioncited by 41
  19. 2022Visual Attention Methods in Deep Learning: An In-Depth Surveycited by 37
  20. 2022TSA-Net: Tube Self-Attention Network for Action Quality Assessmentcited by 36
  21. 2022HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classificationcited by 30
  22. 2021Unsupervised Object Learning via Common Fatecited by 29
  23. 2022Attention Mechanism in Neural Networks: Where it Comes and Where it Goescited by 29
  24. 2022LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Networkcited by 28
  25. 2023E(2)-Equivariant Vision Transformercited by 27
  26. 2021FoveaTer: Foveated Transformer for Image Classificationcited by 26
  27. 2022Interpretable by Design: Learning Predictors by Composing Interpretable Queriescited by 26
  28. 2023Variational Information Pursuit for Interpretable Predictionscited by 25
  29. 2023Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNNcited by 25
  30. 2021Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Controlcited by 24
  31. 2021Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoningcited by 23
  32. 2023Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directionscited by 23
  33. 2023LION: Implicit Vision Prompt Tuningcited by 22
  34. 2021Recurrent Glimpse-based Decoder for Detection with Transformercited by 21
  35. 2025Continuous Thought Machinescited by 21
  36. 2021Human Attention in Fine-grained Classificationcited by 20
  37. 2023Estimating Conditional Mutual Information for Dynamic Feature Selectioncited by 20
  38. 2021A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolutioncited by 19

50 most cited of 344 All 344 (JSON)