AI Paper Atlas

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

Progressive Attention Memory Network for Movie Story Question Answering

Junyeong Kim, Minuk Ma, Kyungsu Kim, Sungjin Kim, Chang D. Yoo

CVPR 2019 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 90 citations (OpenAlex)

Check 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 progressive attention that updates memory using question and answer cues (ablation)PAMN · MovieQA validationaccuracy: 42.03 -> 43.34Improved
Add multiple attention hops (ablation)PAMN · MovieQA validationaccuracy: 42.67 -> 43.34Improved
Use question-conditioned dynamic modality fusion instead of mean fusion (ablation)PAMN · MovieQA validationaccuracy: 42.09 -> 43.34Improved
Use dynamic modality fusion instead of MCB fusion (ablation)PAMN · MovieQA validationaccuracy: 42.89 -> 43.34Improved
Use dynamic modality fusion instead of MFB fusion (ablation)PAMN · MovieQA validationaccuracy: 42.55 -> 43.34Improved
Use dynamic modality fusion instead of Tucker fusion (ablation)PAMN · MovieQA validationaccuracy: 42.89 -> 43.34Improved
Add both Mu and Mg belief corrections (ablation)PAMN · MovieQA validationaccuracy: 39.50 -> 43.34Improved
Add Mg belief correction (ablation)PAMN · MovieQA validationaccuracy: 41.76 -> 43.34Improved
Add Mu belief correction (ablation)PAMN · MovieQA validationaccuracy: 40.86 -> 43.34Improved
Increase attention hops from 1/1 to 2/2 (ablation)PAMN with pooling 24/16 and correction weights 1/0.5 · MovieQA validationaccuracy: 42.67 -> 43.34Improved
Increase attention hops from 2/2 to 3/3 (ablation)PAMN with pooling 24/16 and correction weights 1/0.5 · MovieQA validationaccuracy: 43.34 -> 42.55Hurt
Use pooling size/stride 80/60 rather than 24/16 (ablation)PAMN with 1/1 hops and correction weights 1/0.5 · MovieQA validationaccuracy: 42.67 -> 41.20Hurt

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