1 dataset found

Formats: JSON Tags: Referring Expression Comprehension

Filter Results

  • 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).