2 datasets found

Groups: Natural Language Processing

Filter Results
  • ScanRefer

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

    The dataset used in the paper is a benchmark for referring expression grounding, containing 142,210 referring expressions for 50,000 referents in 19,994 images.