3260 papers • 126 benchmarks • 313 datasets
Given an image and a corresponding caption, the Phrase Grounding task aims to ground each entity mentioned by a noun phrase in the caption to a region in the image. Source: Phrase Grounding by Soft-Label Chain Conditional Random Field
(Image credit: Papersgraph)
These leaderboards are used to track progress in phrase-grounding-18
Use these libraries to find phrase-grounding-18 models and implementations
No datasets available.
Adding a benchmark result helps the community track progress.