7 datasets found

This dataset is used in the paper to evaluate the performance of the TranSTR architecture.

Video question answering (VideoQA) is an essential task in vision-language understanding, which has attracted numerous research attention recently. Nevertheless, existing works...

A dataset and architecture for visual reasoning with a working memory.

TVQA is a video question answering dataset collected from 6 long-running TV shows from 3 genres. There are 21,793 video clips in total for QA collection, accompanied with...

Video question answering (VideoQA) requires systems to understand the visual information and infer an answer for a natural language question from it.

The MSVD-QA dataset is a benchmark for video question answering, containing 1,970 videos with multiple-choice questions.

The ORBIT dataset is a collection of videos recorded on cell phones by people who are blind or low-vision. The dataset consists of 3,822 videos with 486 object categories...