NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results
Andrey Moskalenko, Alexey Bryncev, Ivan Kosmynin, Kira Shilovskaya, Mikhail Erofeev + 38 more
TLDR
NTIRE 2026 challenge overview: methods and results for video saliency prediction using a new 2,000-video dataset and crowdsourced fixations.
Key contributions
- Presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction.
- Introduced a novel dataset of 2,000 diverse videos with an open license for the challenge.
- Saliency maps collected using crowdsourced mouse tracking from over 5,000 assessors.
- Attracted over 20 teams, with 7 passing the final phase with code review.
Why it matters
This paper documents a significant challenge in video saliency, providing a new large-scale dataset and evaluation benchmark. It fosters research and development in automatic saliency prediction, making valuable resources publicly available for future research.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.