AI Paper Atlas

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

Deconfounded Visual Grounding

Jianqiang Huang, Yu Qin, Jiaxin Qi, Qianru Sun, Hanwang Zhang

AAAI 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 30 citations (OpenAlex)

Read the paper

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 RED to LBYLLBYL · RefCOCO testBAcc@0.5%: 74.15 -> 77.66Improved
Add RED to LBYLLBYL · RefCOCO+ testBAcc@0.5%: 59.49 -> 62.20Improved
Add RED to LBYLLBYL · RefCOCOgAcc@0.5%: 69.06 -> 71.11; 68.34 -> 70.67Improved
Add RED to LBYLLBYL · ReferItGameAcc@0.5%: 66.51 -> 67.27Improved
Add RED to Yang's-V1†Yang's-V1† (YOLO-V4) · Flickr30K EntitiesAcc@0.5%: 70.25 -> 70.50Improved
Use an autoencoder on image and language features rather than language features alone (ablation)Yang's-V1† + RED · RefCOCO+ and RefCOCOgAcc@0.5%: 66.74 vs 66.87; 57.23 vs 57.51; 69.01 vs 69.46; 68.55 vs 69.51Hurt
Add attention to image features alongside language features (ablation)Yang's-V1† + RED · RefCOCO+ and RefCOCOgAcc@0.5%: 65.57 vs 66.87; 56.37 vs 57.51; 67.83 vs 69.46; 68.11 vs 69.51Hurt
Add RED to Yang's-V1†Yang's-V1† · Visual grounding inferencelatency per sample: 24.56ms -> 26.53msHurt

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