SNLI-VE

SNLI-VE is the dataset proposed for the Visual Entailment (VE) task investigated in Visual Entailment Task for Visually-Grounded Language Learning accpeted to NeurIPS 2018 ViGIL workshop). SNLI-VE is built on top of SNLI and Flickr30K. The problem that VE is trying to solve is to reason about the relationship between a

Papers using SNLI-VE (5)

UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding2023 · 2 citesAnswer-Me: Multi-Task Open-Vocabulary Visual Question Answering2022 · 16 citesIdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models2023 · 4 citesMixGen: A New Multi-Modal Data Augmentation2022 · 2 citesCompound Tokens: Channel Fusion for Vision-Language Representation Learning2022 · 2 cites