4 datasets found

Formats: JSON Tags: Referring Image Segmentation

Filter Results

  • ReferIt

    Referring image segmentation aims at localizing all pixels of the visual objects described by a natural language sentence.

  • G-Ref

    G-Ref is a dataset for referring image segmentation, comprising 104K referring language expressions for around 55K objects in about 27K images.

  • 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.

  • RefCOCO, RefCOCO+, and RefCOCOg

    Visual Grounding is a task that aims to locate a target object according to a natural language expression. The dataset used in this paper is RefCOCO, RefCOCO+, and RefCOCOg.
You can also access this registry using the API (see API Docs).