Skip to content

Code for "Saliency Prediction of Sports Videos: A Large-Scale Database and a Self-Adaptive Approach", ICASSP 2024

Notifications You must be signed in to change notification settings

MinglangQiao/Sports_saliency

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sports_saliency

This repository provides the database and code for reproducing the results in the paper:

Accepted by ICASSP 2024.

Database

image

The database can be download from Here. Due to the copyright of the videos, the database is password protected, please send me email (minglangqiao@buaa.edu.cn) to get the password of the download link.

Test Code

python test_single_video.py --gpu 6 --use_sound True --residual_fusion True \
    --test_video_path "/xx/all_1000video/out_of_play_(2).mp4" \
    --save_path "/xx/model_output/" \
    --file_weight "/xx/VSTNet_pseudo_test.pth"

The pre-trained model can be download from Here.

Training Code

TO BE UPDATE

About

Code for "Saliency Prediction of Sports Videos: A Large-Scale Database and a Self-Adaptive Approach", ICASSP 2024

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages