Textual Temporal Understanding Dataset
Temporal Reasoning Transfer from Text to Video, ICLR 2025
Project Page:
https://video-t3.github.io/
In each json file, we provide LLaVA-style text QA samples, using the synthesization method described in our paper.
For example:
[
{
"from": "human",
"value": "Based on the following captions describing keyframes of a video, answer the next question.\n\nCaptions:\nThe image displays a circular emblem with a metallic appearance, conveying a… See the full description on the dataset page:
https://huggingface.co/datasets/MMInstruction/Video-T3-QA.
