Benchmark Almanac

Xuelong Li

We track 3 benchmarks that Xuelong Li made or helped make.

0 in use 1 with public code 0 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
RSICD Models describe aerial scenes in a sentence. The authors provide five reference captions per image and reserve 1,093 images for testing. Detection and captioning Sep 2017 Not in cards
Sydney-Captions Models describe land use in aerial images of Sydney. The dataset pairs 613 images with five human captions each. Detection and captioning Jul 2016 Not in cards
UCM-Captions Models describe aerial land use scenes from the UC Merced collection. The dataset pairs 2,100 images with five human captions each. Detection and captioning Jul 2016 Not in cards