MMInstruction/Video-T3-QA

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.

<iframe src="https://silytics.si/embed/item/8185e5f7-ebef-4006-862c-3125e7f7eaab" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.