mlsanityData to 7 Oct 2026

Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model

arXiv 1611.09571 ↗First posted 29 Nov 2016cs.CVcited by 91

Not on the map. Why?

Abstract (arXiv)

Data-driven saliency has recently gained a lot of attention thanks to the use of Convolutional Neural Networks for predicting gaze fixations. In this paper we go beyond standard approaches to saliency prediction, in which gaze maps are computed with a feed-forward network, and present a novel model which can predict accurate saliency maps by incorporating neural attentive mechanisms. The core of our solution is a Convolutional LSTM that focuses on the most salient regions of the input image to iteratively refine the predicted saliency map. Additionally, to tackle the center bias typical of human eye fixations, our model can learn a set of prior maps generated with Gaussian functions. We show, through an extensive evaluation, that the proposed architecture outperforms the current state of the art on public saliency prediction datasets. We further study the contribution of each key component to demonstrate their robustness on different scenarios.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 28; 2022: 9; 2023: 13; 2024: 20; 2025: 9; 2026: 10.

91 papers.

Sort:

By area:

  1. 2020Predicting Goal-directed Human Attention Using Inverse Reinforcement Learningcited by 53
  2. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  3. 2021TranSalNet: Towards perceptually relevant visual saliency predictioncited by 44
  4. 2019MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learningcited by 29
  5. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  6. 2021Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysiscited by 25
  7. 2023TempSAL -- Uncovering Temporal Information for Deep Saliency Predictioncited by 25
  8. 2021ScanGAN360: A Generative Model of Realistic Scanpaths for 360circ Imagescited by 23
  9. 2023Unifying Top-down and Bottom-up Scanpath Prediction Using Transformerscited by 22
  10. 2021Image Composition Assessment with Saliency-augmented Multi-pattern Poolingcited by 21
  11. 2021Spatio-Temporal Self-Attention Network for Video Saliency Predictioncited by 19
  12. 2023Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embeddingcited by 19
38 more
  1. 2022Saliency in Augmented Realitycited by 17
  2. 2024GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpathscited by 15
  3. 2021Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservationcited by 14
  4. 2021Understanding Visual Saliency in Mobile User Interfacescited by 13
  5. 2023Eye-tracked Virtual Reality: A Comprehensive Survey on Methods and Privacy Challengescited by 12
  6. 2024Beyond Average: Individualized Visual Scanpath Predictioncited by 12
  7. 2024SUM: Saliency Unification through Mamba for Visual Attention Modelingcited by 12
  8. 2024CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusioncited by 12
  9. 2021Instance-Level Relative Saliency Ranking with Graph Reasoningcited by 9
  10. 2021MAAD: A Model and Dataset for "Attended Awareness" in Drivingcited by 9
  11. 2021SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networkscited by 9
  12. 2022A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!cited by 9
  13. 2024Trends, Applications, and Challenges in Human Attention Modellingcited by 9
  14. 2021SALYPATH: A Deep-Based Architecture for visual attention predictioncited by 7
  15. 2023Audio-visual Saliency for Omnidirectional Videoscited by 7
  16. 2023UniAR: A Unified model for predicting human Attention and Responses on visual contentcited by 7
  17. 2024How is Visual Attention Influenced by Text Guidance? Database and Modelcited by 7
  18. 2024AIM 2024 Challenge on Video Saliency Prediction: Methods and Resultscited by 7
  19. 2026Agentic Retoucher for Text-To-Image Generationcited by 7
  20. 2021Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Modelcited by 6
  21. 2022A domain adaptive deep learning solution for scanpath prediction of paintingscited by 6
  22. 2021Scanpath Prediction on Information Visualisationscited by 5
  23. 2024OAT: Object-Level Attention Transformer for Gaze Scanpath Predictioncited by 5
  24. 2024Data Augmentation via Latent Diffusion for Saliency Predictioncited by 5
  25. 2025DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Imagescited by 5
  26. 2022Improving saliency models' predictions of the next fixation with humans' intrinsic cost of gaze shiftscited by 4
  27. 2023Scanpath Prediction in Panoramic Videos via Expected Code Length Minimizationcited by 4
  28. 2023What Do Deep Saliency Models Learn about Visual Attention?cited by 4
  29. 2024How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Modelcited by 4
  30. 2021A Gated Fusion Network for Dynamic Saliency Predictioncited by 3
  31. 2021Bio-Inspired Representation Learning for Visual Attention Predictioncited by 3
  32. 2024Predicting Visual Attention in Graphic Design Documentscited by 3
  33. 2025Measuring and Predicting Where and When Pathologists Focus their Visual Attention while Grading Whole Slide Images of Cancercited by 3
  34. 2021Where to look at the movies : Analyzing visual attention to understand movie editingcited by 2
  35. 2021Modeling Object Dissimilarity for Deep Saliency Predictioncited by 2
  36. 2021Audio-Visual Collaborative Representation Learning for Dynamic Saliency Predictioncited by 2
  37. 2022A Probabilistic Time-Evolving Approach to Scanpath Predictioncited by 2
  38. 2022GASP: Gated Attention For Saliency Predictioncited by 2

50 most cited of 91 All 91 (JSON)