Visual-7W

Emerging

4papers using it

2016first seen

The Visual-7W dataset is a benchmark used for evaluating multiple choice visual question answering models, containing images paired with questions and answers.

🔎 Find this dataset

Papers using Visual-7W (4)

Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding2016 · 394 cites

Compact Trilinear Interaction for Visual Question Answering2019 · 14 cites

Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering2018 · 10 cites

Recurrent and Contextual Models for Visual Question Answering2017