AI Paper Atlas

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

Cross Modal Fine-grained Alignment via Granularity-aware and Region-uncertain Modeling

Jiale Liu, Haoming Zhou, Yishu Liu, Bingzhi Chen, Yuncheng Jiang

AAAI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 4 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 Significance-aware Adapter (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 502.8 -> 516.2Improved
add Granularity-aware Adapter (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 507.0 -> 516.2Improved
add region prompts (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 503.3 -> 516.2Improved
add region-level uncertainty modeling (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 508.3 -> 516.2Improved
add original-feature contrastive loss (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 487.2 -> 516.2Improved
add significance-aware contrastive loss (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 505.9 -> 516.2Improved
add uncertainty-aware contrastive loss (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 501.6 -> 516.2Improved
add semantic consistency (reconstruction) loss (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 513.2 -> 516.2Improved
add KL and entropy regularization (ablation)GRM · Flickr30K 1k (ViT-Base-224)rSum: 514.2 -> 516.2Improved
increase number of region prompts beyond 5 (ablation)GRM with ViT-Base-224 · Flickr30KrSumHurt
use 50 region prompts with Swin-Base-224 backbone (ablation)GRM with Swin-Base-224 · Flickr30KrSumImproved
put heavy weight c=0.6 on uncertainty-aware alignment loss (a=b=0.2) (ablation)GRM · Flickr30KrSumHurt

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