Deep Video Understanding (DVU) Dataset

Description

The DVU dataset consists of 10 creative common movies for training and 4 creative common movies for testing used in the Deep Video Understanding grand challenges in 2020 and 2021. Total duration is about 17 hr.

Resources

Name Format Description Link
0 Training dataset applied to DVU Grand Challenge at ACM Multimedia Grand Challenges of 2020, 2021 and ACM Multimedia Asia Grand Challenge of 2021. https://www-nlpir.nist.gov/projects/trecvid/dvu/training/
0 This is the testing dataset used in 2021 for the ACM MM Grand Challenge and ACM MM Asia Grand Challenge. https://www-nlpir.nist.gov/projects/trecvid/dvu/testing/

Tags

  • multimodal-integration
  • multimedia-understanding
  • artificial-intelligence

Topics

Categories