AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Weakly-Supervised Visual Grounding of Phrases With Linguistic Structures

Fanyi Xiao, Leonid Sigal, Yong Jae Lee

CVPR 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 119 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 parent-child and sibling structural constraints to discriminative trainingphrase-grounding model · Visual Genomepointing game accuracy: 0.230 -> 0.244Improved
add parent-child constraint (ablation)phrase-grounding model · Visual Genomepointing game accuracy: 0.230 -> 0.236Improved
add sibling constraint alone (ablation)phrase-grounding model · Visual Genomepointing game accuracy: 0.230 -> 0.231No clear effect
train using phrases rather than noun tokensphrase-grounding model · Visual Genomepointing game accuracy: 0.222 -> 0.230Improved
add parent-child and sibling structural constraints to discriminative trainingphrase-grounding model · MS COCO val2014Avg mAP: 0.203 -> 0.251Improved
add parent-child constraint (ablation)phrase-grounding model · MS COCO val2014Avg mAP: 0.203 -> 0.219Improved
add sibling constraint (ablation)phrase-grounding model · MS COCO val2014Avg mAP: 0.203 -> 0.211Improved
train using noun tokens rather than phrasesphrase-grounding model · MS COCO val2014Avg mAP: 0.203 -> 0.238Improved
combine parent-child and sibling constraints rather than use either constraint alone (ablation)phrase-grounding model · Visual Genomepointing game accuracy: PC 0.236; SIB 0.231; Ours 0.244Improved
combine parent-child and sibling constraints rather than use either constraint alone (ablation)phrase-grounding model · MS COCO val2014Avg mAP: PC 0.219; SIB 0.211; Ours 0.251Improved

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