[KongchangAI]
Benchmark

TORS

A surgical scene captioning evaluation dataset used to test model performance on the surgical image captioning task.

Timeline (last 90 days)

Nov 9

On the TORS dataset, GRAC achieves a CIDEr-D score of 5.06, and the strongest baseline achieves 3.80.

Unverified50%

All Facts (1)

Source Articles