AI Paper Atlas

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

Combining Multiple Cues for Visual Madlibs Question Answering

Tatiana Tommasi, Arun Mallya, Bryan A. Plummer, Svetlana Lazebnik, Alexander C. Berg, Tamara L. Berg

IJCV 2018 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 13 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 Places scene features to ImageNet baseline (ablation)ImageNet fc7 · Visual Madlibs Easy, Sceneaccuracy: 87.73 -> 89.04Improved
add Places scene features to ImageNet baseline (ablation)ImageNet fc7 · Visual Madlibs Hard, Sceneaccuracy: 70.94 -> 73.22Improved
add Attribute person-box features to baseline (ablation)ImageNet fc7 · Visual Madlibs Easy, Person's Attributeaccuracy: 53.32 -> 64.50Improved
add HICO person-box features to baseline (ablation)ImageNet fc7 · Visual Madlibs Easy, Person's Activityaccuracy: 83.89 -> 87.46Improved
add Color object features to baseline (ablation)ImageNet fc7 · Visual Madlibs Easy, Object's Attributeaccuracy: 50.15 -> 59.50Improved
add object-box ImageNet features to baseline (ablation)ImageNet fc7 · Visual Madlibs Easy, Object's Affordanceaccuracy: 80.56 -> 87.20Improved
add Color features to object-box ImageNet baseline (ablation)ImageNet fc7 · Visual Madlibs Easy, Object's Affordanceaccuracy: 87.20 -> 82.32Hurt
add Attribute labels to HICO+MPII label combination (ablation)HICO+MPII labels · Visual Madlibs Easy, Person's Attributeaccuracy: 59.37 -> 68.43Improved
use HICO+MPII labels instead of best fc7 cue (ablation)best single fc7 cue · Visual Madlibs Easy, Interesting/Past/Future/Locationaccuracy: small dropHurt
add Person and Object selection scores to HICO+MPII+Attr CCA (ablation)HICO+MPII+Attr CCA · Visual Madlibs Hard, Pastaccuracy: 58.17 -> 58.29 -> 59.60Improved
combine all CCA cue scores into learned ensemble (L1) (ablation)best single cue · Visual Madlibs, average Easyaccuracy: 77.30 -> 79.19Improved
combine all CCA cue scores into learned ensemble (L1) (ablation)best single cue · Visual Madlibs, average Hardaccuracy: 60.03 -> 61.52Improved

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