Video Saliency Prediction Challenge 2024

Video Saliency Prediction Challenge

G&M Lab head: Dr. Dmitriy Vatolin
Organizers:
Alexey Bryncev,
Andrey Moskalenko


Video Saliency Prediction Challenge

  • Large multimodal high resolution reliable Video Saliency dataset
  • Evaluating metrics on four metrics: CC, SIM, NSS, AUC Judd
  • The score on the hidden part of the test set will not be shown until the end of the challenge


Task

The task is to develop a Video Saliency Prediction method.

Motivation

Saliency maps are widely used in areas such as video compression, medicine, and the advertising industry. Our competition is aimed at revealing the best model for the Video Saliency Prediction task.

Dataset

We provide a new dataset consisting of Ground-Truth saliency maps for training and evaluating participant’s Video Saliency Prediction methods. Dataset key-features:

  • Multimodality: movie fragments, sports streams, and live captions;
  • High resolution;
  • Audio information;
  • Large size: ~ 1500 videos;
  • Fixations from ~50 observers;

The dataset will be available as soon as the challenge starts.

Organizers from Graphics & Media Lab

Andrey Moskalenko

Alexey Bryncev

He is currently in his 4th year of undergraduate studies. Alexey research interests include Video Saliency data collection, prediction, and evaluation.

09 May 2024
See Also
Real-World Stereo Color and Sharpness Mismatch Dataset
Download new real-world video dataset of stereo color and sharpness mismatches
Super-Resolution Quality Metrics Benchmark
Discover 66 Super-Resolution Quality Metrics and choose the most appropriate for your videos
Site structure