SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes

2017/07/11 by Marc Assens, Kevin McGuinness, Assens, Marc +7 · 4 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimedia (cs.MM) #Visual Attention and Saliency Detection #cs.CV #cs.MM

paper · pdf · doi:10.48550/arxiv.1707.03123

Winner of the Best Scan-path Award at the Salient360!: Visual attention modeling for 360 degrees Images Grand Challenge of ICME 2017. Presented at the ICCV 2017 Workshop on Egocentric Perception, Interaction and Computing (EPIC)

openalex publication_date 2017/07/11 · arxiv created 2017/08/17 · arxiv updated 2017/08/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce SaltiNet, a deep neural network for scanpath prediction trained on 360-degree images. The model is based on a temporal-aware novel representation of saliency information named the saliency volume. The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes. Sampling strategies over these volumes are used to generate scanpaths over the 360-degree images. Our experiments show the advantages of using saliency volumes, and how they can be used for related tasks. Our source code and trained models available at https://github.com/massens/saliency-360salient-2017.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
• ImageNet classification with deep convolutional neural networks
• DeepGaze II: Reading fixations from deep features trained on object recognition
• A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection

Cited by

• DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images
• Viewport-Aware Deep Reinforcement Learning Approach for 360^o Video Caching
• Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning
• Deep Learning for Content-Based Personalized Viewport Prediction of 360-Degree VR Videos
• Few-shot Personalized Scanpath Prediction

Related

• SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images
• ScanDTM: A Novel Dual-Temporal Modulation Scanpath Prediction Model for Omnidirectional Images
• A Simple and efficient deep Scanpath Prediction
• PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks
• SALYPATH: A Deep-Based Architecture for visual attention prediction