NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results
- URL: http://arxiv.org/abs/2604.14816v1
- Date: Thu, 16 Apr 2026 09:36:58 GMT
- Title: NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results
- Abstract summary: This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction.<n>The goal of the challenge participants was to develop automatic saliency map prediction methods for the provided video sequences.<n>The novel dataset of 2,000 diverse videos with an open license was prepared for this challenge.
- Score: 123.0965074023145
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results [107.50621348972328]
The NTIRE 2025 XGC Quality Assessment Challenge will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025.<n>The challenge is divided into three tracks, including user generated video, AI generated video and talking head.<n>Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.
arXiv Detail & Related papers (2025-06-03T13:39:57Z) - NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results [73.23764765210825]
This paper presents an overview of the NTIRE 2025 Challenge on Video Enhancement.<n>The challenge constructed a set of 150 user-generated content videos without reference ground truth.<n>The goal of the participants was to develop an algorithm capable of improving the visual quality of such videos.
arXiv Detail & Related papers (2025-05-05T20:06:11Z) - AIM 2024 Challenge on Video Saliency Prediction: Methods and Results [105.09572982350532]
This paper reviews the Challenge on Video Saliency Prediction at AIM 2024.
The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences.
arXiv Detail & Related papers (2024-09-23T08:59:22Z) - NTIRE 2024 Quality Assessment of AI-Generated Content Challenge [141.37864527005226]
The challenge is divided into the image track and the video track.
The winning methods in both tracks have demonstrated superior prediction performance on AIGC.
arXiv Detail & Related papers (2024-04-25T15:36:18Z) - NTIRE 2023 Quality Assessment of Video Enhancement Challenge [97.809937484099]
This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge.
The challenge is to address a major challenge in the field of video processing, namely, video quality assessment (VQA) for enhanced videos.
The challenge has a total of 167 registered participants.
arXiv Detail & Related papers (2023-07-19T02:33:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.