AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

VizWiz Grand Challenge: Answering Visual Questions From Blind People

Danna Gurari, Qing Li, Abigale J. Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, Jeffrey P. Bigham

CVPR 2018 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 612 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Fine-tune VQA V2.0 models on VizWizQ+I, Q+I+A, and Q+I+BUA · VizWiz testAccuracy: 0.137 -> 0.466; 0.145 -> 0.469; 0.134 -> 0.475Improved
Train the models from scratch on VizWizQ+I, Q+I+A, and Q+I+BUA · VizWiz testAccuracy: 0.137 -> 0.465; 0.145 -> 0.469; 0.134 -> 0.469Improved
Use VizWiz training rather than fine-tuningQ+I, Q+I+A, and Q+I+BUA · VizWiz testAccuracy: 0.466 vs 0.465; 0.469 vs 0.469; 0.475 vs 0.469No clear effect
Add attention to image and question informationQ+I · VizWiz testAccuracy: 0.137 -> 0.145Improved
Add image features to question featuresAnswerability classifier · VizWiz test answerabilityAverage precision: 0.490 -> 0.717Improved
Add question information to image featuresAnswerability classifier · VizWiz test answerabilityAverage precision: 0.640 -> 0.717Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy