AI Paper Atlas

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

Multi-Modal Factorized Bilinear Pooling With Co-Attention Learning for Visual Question Answering

Zhou Yu, Jun Yu, Jianping Fan, Dacheng Tao

ICCV 2017 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 810 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
add l2 normalization after MFB output (ablation)MFB (k=5, o=1000) · VQA test-dev Open-Endedaccuracy: 57.7 -> 60.9Improved
add power normalization after MFB output (ablation)MFB (k=5, o=1000) · VQA test-dev Open-Endedaccuracy: 60.4 -> 60.9Improved
add both power and l2 normalization (ablation)MFB (k=5, o=1000) · VQA test-dev Open-Endedaccuracy: 57.3 -> 60.9Improved
increase factor k from 1 to 5 at fixed ko=5000 (ablation)MFB · VQA test-dev Open-Endedaccuracy: 60.4 -> 60.9Improved
increase factor k from 5 to 10 (ko=5000) (ablation)MFB · VQA test-dev Open-Endedaccuracy: 60.9 -> 60.6No clear effect
increase output dimension o beyond 1000 (2000, 4000) (ablation)MFB (k=5) · VQA test-dev Open-Endedaccuracy: 60.9 -> 60.7 -> 60.4Hurt
reduce output dimension o to 200 (ablation)MFB (k=5) · VQA test-dev Open-Endedaccuracy: 60.9 -> 59.8Hurt
replace MCB/MLB fusion with MFB (ablation)bilinear fusion baseline · VQA test-dev Open-Endedaccuracy: 59.8 -> 60.9Improved
add question attention (co-attention) to image attention (ablation)MFB+Att · VQA test-dev Open-Endedaccuracy: 64.6 -> 65.1Improved
add image attention (ablation)MFB · VQA test-dev Open-Endedaccuracy: 62.2 -> 64.6Improved
concatenate pre-trained GloVe word vectors (ablation)MFB+CoAtt · VQA test-dev Open-Endedaccuracy: 65.1 -> 65.9Improved
add Visual Genome training data (ablation)MFB+CoAtt+GloVe · VQA test-dev Open-Endedaccuracy: 65.9 -> 66.9Improved

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