mlsanityData to 14 Oct 2026

Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet

arXiv 1411.1045 ↗First posted 4 Nov 2014cs.CV q-bio.NC stat.APcited by 60

Not on the map. Why?

Abstract (arXiv)

Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations. This lack in performance has been attributed to an inability to model the influence of high-level image features such as objects. Recent seminal advances in applying deep neural networks to tasks like object recognition suggests that they are able to capture this kind of structure. However, the enormous amount of training data necessary to train these networks makes them difficult to apply directly to saliency prediction. We present a novel way of reusing existing neural networks that have been pretrained on the task of object recognition in models of fixation prediction. Using the well-known network of Krizhevsky et al. (2012), we come up with a new saliency model that significantly outperforms all state-of-the-art models on the MIT Saliency Benchmark. We show that the structure of this network allows new insights in the psychophysics of fixation selection and potentially their neural implementation. To train our network, we build on recent work on the modeling of saliency as point processes.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Nov 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 11; 2022: 5; 2023: 12; 2024: 10; 2025: 12; 2026: 9.

60 papers.

Sort:

By area:

  1. 2021DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modelingcited by 56
  2. 2020Predicting Goal-directed Human Attention Using Inverse Reinforcement Learningcited by 53
  3. 2023Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attentioncited by 38
  4. 2023TempSAL -- Uncovering Temporal Information for Deep Saliency Predictioncited by 25
  5. 2023Unifying Top-down and Bottom-up Scanpath Prediction Using Transformerscited by 22
  6. 2022Target-absent Human Attentioncited by 20
  7. 2021Spatio-Temporal Self-Attention Network for Video Saliency Predictioncited by 19
  8. 2021Deep Saliency Prior for Reducing Visual Distractioncited by 17
  9. 2024Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognitioncited by 17
  10. 2024ViSaRL: Visual Reinforcement Learning Guided by Human Saliencycited by 12
  11. 2024SUM: Saliency Unification through Mamba for Visual Attention Modelingcited by 12
  12. 2025Transformer brain encoders explain human high-level visual responsescited by 10
38 more
  1. 2025Where, What, Why: Towards Explainable Driver Attention Predictioncited by 10
  2. 2021SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networkscited by 9
  3. 2022The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networkscited by 9
  4. 2026Gaze-Regularized Vision-Language-Action Models for Robotic Manipulationcited by 9
  5. 2021Attention mechanisms and deep learning for machine vision: A survey of the state of the artcited by 8
  6. 2021SALYPATH: A Deep-Based Architecture for visual attention predictioncited by 7
  7. 2023UniAR: A Unified model for predicting human Attention and Responses on visual contentcited by 7
  8. 2024AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scalecited by 7
  9. 2024How is Visual Attention Influenced by Text Guidance? Database and Modelcited by 7
  10. 2025Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Predictioncited by 7
  11. 2023SimpSON: Simplifying Photo Cleanup with Single-Click Distracting Object Segmentation Networkcited by 5
  12. 2024Data Augmentation via Latent Diffusion for Saliency Predictioncited by 5
  13. 2025DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Imagescited by 5
  14. 2024GazeFusion: Saliency-Guided Image Generationcited by 4
  15. 2024TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processescited by 4
  16. 2025Modeling Saliency Dataset Biascited by 4
  17. 2021Bio-Inspired Representation Learning for Visual Attention Predictioncited by 3
  18. 2021Modeling Object Dissimilarity for Deep Saliency Predictioncited by 2
  19. 2022Context-empowered Visual Attention Prediction in Pedestrian Scenarioscited by 2
  20. 2023Learning Saliency From Fixationscited by 2
  21. 2025FSDAM: Few-Shot Driving Attention Modeling via Vision-Language Couplingcited by 2
  22. 2025Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformercited by 2
  23. 2021A Simple and efficient deep Scanpath Predictioncited by 1
  24. 2022Where and What: Driver Attention-based Object Detectioncited by 1
  25. 2022Clustered Saliency Predictioncited by 1
  26. 2023Multi-Scale Estimation for Omni-Directional Saliency Maps Using Learnable Equator Biascited by 1
  27. 2024Learning Gaussian Representation for Eye Fixation Predictioncited by 1
  28. 2024Unlocking Comics: The AI4VA Dataset for Visual Understandingcited by 1
  29. 2026SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptationcited by 1
  30. 2026From Scene to Object: Text-Guided Dual-Gaze Predictioncited by 1
  31. 2026DeepGaze3.5-VL: Modeling Scanpaths via Autoregressive Token Predictioncited by 1
  32. 2021Noise-Aware Video Saliency Predictioncited by 0
  33. 2021Benchmarking human visual search computational models in natural scenes: models comparison and reference datasetscited by 0
  34. 2023Semantic Segmentation Enhanced Transformer Model for Human Attention Predictioncited by 0
  35. 2023Physics-Inspired Interpretability Of Machine Learning Modelscited by 0
  36. 2023ViDaS Video Depth-aware Saliency Networkcited by 0
  37. 2023Using Saliency and Cropping to Improve Video Memorabilitycited by 0
  38. 2023Teaching Unknown Objects by Leveraging Human Gaze and Augmented Reality in Human-Robot Interactioncited by 0

50 most cited of 60 All 60 (JSON)