AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Learning Cross-Modal Context Graph for Visual Grounding

Yongfei Liu, Bo Wan, Xiaodan Zhu, Xuming He

AAAI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 85 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 cross-modal graph approach with ResNet-101 instead of DDPNvisual grounding · Flickr30K Entities testaccuracy (%): 73.30 -> 76.74Improved
use the cross-modal graph approach with ResNet-50 instead of SeqGROUNDvisual grounding · Flickr30K Entities testaccuracy (%): 61.60 -> 67.90Improved
add phrase graph network (ablation)visual grounding baseline · Flickr30K Entities valaccuracy (%): 73.46 -> 74.40Improved
add proposal pruning guided by PGN (ablation)baseline + PGN · Flickr30K Entities valaccuracy (%): 74.40 -> 75.50Improved
add visual object graph network (ablation)baseline + PGN + proposal pruning · Flickr30K Entities valaccuracy (%): 75.50 -> 75.85Improved
add structured prediction with global relation matching (ablation)baseline + PGN + proposal pruning + VOGN · Flickr30K Entities valaccuracy (%): 75.85% to 76.19%Improved
remove phrase relation features (ablation)phrase graph network · Flickr30K Entities valaccuracy (%): 74.40 -> 74.11Hurt
remove phrase relation features (ablation)PGN + proposal pruning · Flickr30K Entities valaccuracy (%): 75.50 -> 75.32Hurt
remove phrase and visual relation features (ablation)PGN + proposal pruning + VOGN · Flickr30K Entities valaccuracy (%): 75.85 -> 75.44Hurt
reduce proposals per phrase from K=10 to K=5 (ablation)cross-modal graph model · Flickr30K Entities valaccuracy (%): 76.19% to 74.97%Hurt
increase proposals per phrase from K=10 to K=20 (ablation)cross-modal graph model · Flickr30K Entities valaccuracy (%): 76.19 -> 76.07No clear effect

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