AI Paper Atlas

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

Learning to Answer Questions from Image Using Convolutional Neural Network

Lin Ma, Zhengdong Lu, Hang Li

AAAI 2016 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 263 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
Use the end-to-end CNN with image, question, and multimodal convolution components instead of Neural-Image-QAImage QA model · DAQUAR-All, single wordaccuracy: 19.43 -> 24.49Improved
Use the end-to-end CNN instead of Neural-Image-QAImage QA model · DAQUAR-Reduced, single wordaccuracy: 34.68 -> 42.76Improved
Use the end-to-end CNN instead of VSE FULLImage QA model · COCO-QAaccuracy: 57.84 -> 58.40Improved
Add multimodal convolution to fuse image and question representations rather than simply concatenate them (ablation)Proposed CNN · COCO-QAaccuracy: 56.77 -> 58.40Improved
Add the image representation (ablation)Proposed CNN · COCO-QAaccuracy: 37.84 -> 58.40Improved
Preserve natural word order instead of randomly reshuffling question words (ablation)Proposed CNN · COCO-QAaccuracy: 40.74 versus 58.40Improved
Use bidirectional 2-VIS+BLSTM instead of VIS+LSTMVSE · DAQUAR-Reduced, single wordaccuracy: 34.41 -> 35.78Improved

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