VQA-CP v-2

'VQA-CP v-2' is a benchmark dataset for Visual Question Answering that contains images and corresponding questions, used to evaluate the performance of models in predicting answers based on visual and textual inputs.

Papers using VQA-CP v-2 (8)

Integrating Object Interaction Self-Attention and GAN-Based Debiasing for Visual Question Answering2025MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models2025Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation2025MUREL: Multimodal Relational Reasoning for Visual Question Answering2019 · 24 citesAnswer Questions with Right Image Regions: A Visual Attention Regularization Approach2021 · 5 citesOvercoming Language Priors with Self-supervised Learning for Visual Question Answering2020 · 3 citesAn Empirical Study on the Language Modal in Visual Question Answering2023 · 1 citesBarlow constrained optimization for Visual Question Answering2022