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

Abstract

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.

IEEE Transactions on Image Processing 2018

References in corpus (3)

• Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
• Hierarchical Boundary-Aware Neural Encoder for Video Captioning
• Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features

Cited by in corpus (21)

• Contextual Encoder-Decoder Network for Visual Saliency Prediction
• Taming the latency in multi-user VR 360${}^{\circ }$: A QoE-aware deep learning-aided multicast framework
• TranSalNet: Towards perceptually relevant visual saliency prediction
• How is Gaze Influenced by Image Transformations? Dataset and Model
• Understanding Visual Saliency in Mobile User Interfaces
• Spatio-Temporal Self-Attention Network for Video Saliency Prediction
• ScanGAN360: A Generative Model of Realistic Scanpaths for 360${}^{\circ }$ Images
• Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation
• Bio-Inspired Representation Learning for Visual Attention Prediction
• Direction Concentration Learning: Enhancing Congruency in Machine Learning
• Attention Flow: End-to-End Joint Attention Estimation
• Predicting Visual Attention in Graphic Design Documents
• Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model
• Improving saliency models' predictions of the next fixation with humans' intrinsic cost of gaze shifts
• Improving Video Compression With Deep Visual-Attention Models
• Saliency for free: Saliency prediction as a side-effect of object recognition
• A domain adaptive deep learning solution for scanpath prediction of paintings
• Emergence of Human-Like Attention in Self-Supervised Vision Transformers: an eye-tracking study
• Wave Propagation of Visual Stimuli in Focus of Attention
• Visual Fixation-Based Retinal Prosthetic Simulation
• Using Saliency and Cropping to Improve Video Memorability