Evaluating Multimodal Representations on Sentence Similarity:vSTS, Visual Semantic Textual Similarity Dataset

Egileak: 
Oier Lopez de Lacalle, Eneko Agirre, Aitor Soroa
Urtea: 
2017
Artikuluaren erreferentzia: 
ICCV17: second workshop on Closing the Loop Between Vision and Language. Venice, Italy