7 datasets found

Text-to-gaze dataset containing over 90k text descriptions of human gaze behavior.

Localizing moments in video with natural language

ScanRefer is a dataset of 51,583 referring descriptions of 11,046 objects from 800 ScanNet scenes.

Humanoid Reaction Synthesis is pivotal for creating highly interactive and empathetic robots that can seamlessly integrate into human environments, enhancing the way we live,...

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...

Audio captioning is a multi-modal task, focusing on using natural language for describing the contents of general audio. Most audio captioning methods are based on deep neural...

The dataset used for training the Vary-base model, containing natural image-text pairs.