5 datasets found

The MSR-VTT dataset is a large-scale video captioning benchmark that contains 10,000 video clips with 200,000 descriptions.

The MSVD dataset is a public video captioning benchmark that contains 1,970 short video clips with 80,000 descriptions.

A comprehensive, large-scale public dataset relating the visual appearance of fabrics to natural language.

Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most state-of-the-art TVR methods learn image-to-video transfer learning...

The dataset used in the paper is MSR-VTT, a large video description dataset for bridging video and language. The dataset contains 10k video clips with length varying from 10 to...