# ATSal: An Attention Based Architecture for Saliency Prediction in 360 Videos

arXiv: https://arxiv.org/abs/2011.10600 · HTML: https://mlsanity.com/paper/2011.10600/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2020.

## Built on by (most cited first, 19 of 19)

- [Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment](https://mlsanity.com/paper/2305.10983/) (2023)
- [ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers](https://mlsanity.com/paper/2303.06907/) (2023)
- [SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images](https://mlsanity.com/paper/2201.00096/) (2022)
- [Deep-based quality assessment of medical images through domain adaptation](https://mlsanity.com/paper/2210.10533/) (2022)
- [Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization](https://mlsanity.com/paper/2305.02536/) (2023)
- [How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model](https://mlsanity.com/paper/2408.05411/) (2024)
- [Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360-Degree Videos](https://mlsanity.com/paper/2508.20221/) (2025)
- [Perceptual Quality Assessment of Virtual Reality Videos in the Wild](https://mlsanity.com/paper/2206.08751/) (2022)
- [An Inter-observer consistent deep adversarial training for visual scanpath prediction](https://mlsanity.com/paper/2211.07336/) (2022)
- [Spherical Vision Transformer for 360-degree Video Saliency Prediction](https://mlsanity.com/paper/2308.13004/) (2023)
- [Learning Saliency From Fixations](https://mlsanity.com/paper/2311.14073/) (2023)
- [An Integrated System for Spatio-Temporal Summarization of 360-degrees Videos](https://mlsanity.com/paper/2312.02576/) (2023)
- [See360: Novel Panoramic View Interpolation](https://mlsanity.com/paper/2401.03431/) (2024)
- [Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution](https://mlsanity.com/paper/2410.11506/) (2024)
- [WinDB: HMD-free and Distortion-free Panoptic Video Fixation Learning](https://mlsanity.com/paper/2305.13901/) (2023)
- [A Human-Annotated Video Dataset for Training and Evaluation of 360-Degree Video Summarization Methods](https://mlsanity.com/paper/2406.02991/) (2024)
- [TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos](https://mlsanity.com/paper/2509.26208/) (2025)
- [SalFormer360: a transformer-based saliency estimation model for 360-degree videos](https://mlsanity.com/paper/2602.04584/) (2026)
- [OpenSAL360: Open-Source Crowdsourcing Platform for Omnidirectional Video Saliency Collection](https://mlsanity.com/paper/2609.21480/) (2026)

## Abstract (arXiv)

The spherical domain representation of 360 video/image presents many challenges related to the storage, processing, transmission and rendering of omnidirectional videos (ODV). Models of human visual attention can be used so that only a single viewport is rendered at a time, which is important when developing systems that allow users to explore ODV with head mounted displays (HMD). Accordingly, researchers have proposed various saliency models for 360 video/images. This paper proposes ATSal, a novel attention based (head-eye) saliency model for 360degree videos. The attention mechanism explicitly encodes global static visual attention allowing expert models to focus on learning the saliency on local patches throughout consecutive frames. We compare the proposed approach to other state-of-the-art saliency models on two datasets: Salient360! and VR-EyeTracking. Experimental results on over 80 ODV videos (75K+ frames) show that the proposed method outperforms the existing state-of-the-art.