HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Image Sentence Alignment On Valse Counting 2

Métriques

Accuracy (%)
pairwise accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Accuracy (%)
pairwise accuracy
Paper TitleRepository
ViLBERT51.873.7VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
GPT1-69.5VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
CLIP-57.5VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
GPT2-45.3VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
LXMERT49.942.6VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
VisualBERT50.050.0VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
ViLBERT 12-in-166.777.3VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
0 of 7 row(s) selected.