: Unlike standard datasets that only use single-word labels, ViCaS provides holistic video-level captions and detailed segmentation masks for objects. Possible Alternatives
: It contains over 65,500 labeled object tracks and more than 11,000 unique noun phrases describing those objects. Download File VicaTS Vids Pt-2.rar
: The videos average roughly 9.1 seconds in length. : Unlike standard datasets that only use single-word