VQA v-2.0
Emerging5papers using it
2017first seen
The VQA v2.0 dataset is a benchmark that contains images paired with open-ended questions and answers, used to evaluate the performance of Vision Language Models in visual question answering tasks.
Papers using VQA v-2.0 (5)
- Analyzing the Sensitivity of Vision Language Models in Visual Question AnsweringExploring Human-like Attention Supervision in Visual Question AnsweringAnswer-checking in Context: A Multi-modal FullyAttention Network for
Visual Question AnsweringEnhancing Visual Question Answering through Ranking-Based Hybrid
Training and Multimodal FusionCycle-Consistency for Robust Visual Question Answering