2 datasets found

Groups: Object Description

Filter Results
  • RefCOCO+ and RefCOCOg

    The RefCOCO+ and RefCOCOg datasets are benchmarks for referring expression comprehension. They contain images of objects and natural language descriptions of the objects.
  • ScanRefer

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