Image Sentence Alignment On Valse Coreference

Métriques

Accuracy (%)

pairwise accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

			Paper Title
ViLBERT 12-in-1	54.4	75.7	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
GPT2	-	54.5	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
CLIP	-	52.1	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
VisualBERT	50.0	49.5	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
ViLBERT	50.0	47.2	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
LXMERT	49.8	46.8	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
GPT1	-	45.6	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

0 of 7 row(s) selected.

Image Sentence Alignment On Valse Coreference | SOTA | HyperAI