Search papers, labs, and topics across Lattice.
The NTIRE 2026 Challenge on Video Saliency Prediction focused on developing automatic saliency map prediction methods using a novel dataset of 2,000 diverse videos, which were annotated with fixations and saliency maps derived from crowdsourced mouse tracking data from over 5,000 assessors. This challenge attracted participation from over 20 teams, with 7 teams successfully passing the final code review phase, highlighting the competitive nature and collaborative spirit of the research community. The evaluation of submissions was conducted on a subset of 800 test videos using established quality metrics, ensuring robust assessment of the proposed methods.
Over 20 teams vied to decode human attention in video, revealing new insights into saliency prediction techniques.
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.
