ffmpbgrnn / VideoQA

Project Uncovering Temporal Context for Video Question and Answering

Temporal context Video Question Answering

Dataset and source code for the paper Uncovering Temporal Context for Video Question and Answering.

Dataset

• Current dataset is the one we used in our arXiv v1 paper.
• See sample.py for details.

Source code

• Will be available upon request.

Download

• You need to install git-lfs first.
  • Download git-lfs on your OS;
  • Initialize with git lfs install
• If you don't have access to git-lfs, you can download the dataset directly from Google Drive or Baidu Yun.