# DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations

arXiv: https://arxiv.org/abs/1510.02927 · HTML: https://mlsanity.com/paper/1510.02927/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2015.

## Built on by (most cited first, 30 of 48)

- [Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning](https://mlsanity.com/paper/2005.14310/) (2020)
- [Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention](https://mlsanity.com/paper/2303.15274/) (2023)
- [MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/1912.07773/) (2019)
- [Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers](https://mlsanity.com/paper/2303.09383/) (2023)
- [Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback](https://mlsanity.com/paper/2402.02423/) (2024)
- [Spatio-Temporal Self-Attention Network for Video Saliency Prediction](https://mlsanity.com/paper/2108.10696/) (2021)
- [Saliency in Augmented Reality](https://mlsanity.com/paper/2204.08308/) (2022)
- [ViSaRL: Visual Reinforcement Learning Guided by Human Saliency](https://mlsanity.com/paper/2403.10940/) (2024)
- [SUM: Saliency Unification through Mamba for Visual Attention Modeling](https://mlsanity.com/paper/2406.17815/) (2024)
- [Instance-Level Relative Saliency Ranking with Graph Reasoning](https://mlsanity.com/paper/2107.03824/) (2021)
- [Look Twice: A Generalist Computational Model Predicts Return Fixations across Tasks and Species](https://mlsanity.com/paper/2101.01611/) (2021)
- [Attention mechanisms and deep learning for machine vision: A survey of the state of the art](https://mlsanity.com/paper/2106.07550/) (2021)
- [Efficient Zero-shot Visual Search via Target and Context-aware Transformer](https://mlsanity.com/paper/2211.13470/) (2022)
- [How is Visual Attention Influenced by Text Guidance? Database and Model](https://mlsanity.com/paper/2404.07537/) (2024)
- [Shifting Focus with HCEye: Exploring the Dynamics of Visual Highlighting and Cognitive Load on User Attention and Saliency Prediction](https://mlsanity.com/paper/2404.14232/) (2024)
- [Data Augmentation via Latent Diffusion for Saliency Prediction](https://mlsanity.com/paper/2409.07307/) (2024)
- [Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks](https://mlsanity.com/paper/2505.02413/) (2025)
- [DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images](https://mlsanity.com/paper/2509.16767/) (2025)
- [Improving saliency models' predictions of the next fixation with humans' intrinsic cost of gaze shifts](https://mlsanity.com/paper/2207.04250/) (2022)
- [What Do Deep Saliency Models Learn about Visual Attention?](https://mlsanity.com/paper/2310.09679/) (2023)
- [Modeling Saliency Dataset Bias](https://mlsanity.com/paper/2505.10169/) (2025)
- [A Gated Fusion Network for Dynamic Saliency Prediction](https://mlsanity.com/paper/2102.07682/) (2021)
- [Bio-Inspired Representation Learning for Visual Attention Prediction](https://mlsanity.com/paper/2103.05310/) (2021)
- [Where to look at the movies : Analyzing visual attention to understand movie editing](https://mlsanity.com/paper/2102.13378/) (2021)
- [Modeling Object Dissimilarity for Deep Saliency Prediction](https://mlsanity.com/paper/2104.03864/) (2021)
- [Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction](https://mlsanity.com/paper/2109.08371/) (2021)
- [Learning Saliency From Fixations](https://mlsanity.com/paper/2311.14073/) (2023)
- [Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer](https://mlsanity.com/paper/2511.19778/) (2025)
- [Clustered Saliency Prediction](https://mlsanity.com/paper/2207.02205/) (2022)
- [Multi-Scale Estimation for Omni-Directional Saliency Maps Using Learnable Equator Bias](https://mlsanity.com/paper/2309.08139/) (2023)

## Abstract (arXiv)

Understanding and predicting the human visual attentional mechanism is an active area of research in the fields of neuroscience and computer vision. In this work, we propose DeepFix, a first-of-its-kind fully convolutional neural network for accurate saliency prediction. Unlike classical works which characterize the saliency map using various hand-crafted features, our model automatically learns features in a hierarchical fashion and predicts saliency map in an end-to-end manner. DeepFix is designed to capture semantics at multiple scales while taking global context into account using network layers with very large receptive fields. Generally, fully convolutional nets are spatially invariant which prevents them from modeling location dependent patterns (e.g. centre-bias). Our network overcomes this limitation by incorporating a novel Location Biased Convolutional layer. We evaluate our model on two challenging eye fixation datasets -- MIT300, CAT2000 and show that it outperforms other recent approaches by a significant margin.