NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results

TL;DR

This paper overviews the NTIRE 2026 Challenge on Video Saliency Prediction, highlighting the dataset, evaluation, participating teams, and publicly available data and code.

Contribution

It introduces a new diverse video dataset, details the challenge setup, and reports on the participating teams and their methods.

Findings

Over 20 teams participated in the challenge.

7 teams passed the final code review.

The dataset and results are publicly available.

Abstract

This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction. The goal of the challenge participants was to develop automatic saliency map prediction methods for the provided video sequences. The novel dataset of 2,000 diverse videos with an open license was prepared for this challenge. The fixations and corresponding saliency maps were collected using crowdsourced mouse tracking and contain viewing data from over 5,000 assessors. Evaluation was performed on a subset of 800 test videos using generally accepted quality metrics. The challenge attracted over 20 teams making submissions, and 7 teams passed the final phase with code review. All data used in this challenge is made publicly available - https://github.com/msu-video-group/NTIRE26_Saliency_Prediction.