Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Visual-7W

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Question AnsweringVisual-7W pointing questions
Accuracy72.53
4
Referring Expression GroundingVisual 7W (test)
Accuracy83.35
3
Showing 2 of 2 rows