EndoVis-18
A public benchmark dataset for surgical scene understanding and captioning, used to evaluate the performance of surgical image captioning models.
Timeline (last 90 days)
On the EndoVis-18 benchmark, GRAC achieves a CIDEr-D score of 5.88, SGT achieves 4.23, and the strongest traditional Transformer baseline achieves 3.36.
On the factual consistency metric of the EndoVis-18 benchmark, GRAC's instrument-action-target triplet set accuracy reaches 52.6%, SGT reaches 32.7%, and the strongest traditional baseline reaches 26.2%.
All Facts (2)
On the EndoVis-18 benchmark, GRAC achieves a CIDEr-D score of 5.88, SGT achieves 4.23, and the strongest traditional Transformer baseline achieves 3.36.
50%UnverifiedOn the factual consistency metric of the EndoVis-18 benchmark, GRAC's instrument-action-target triplet set accuracy reaches 52.6%, SGT reaches 32.7%, and the strongest traditional baseline reaches 26.2%.
50%