AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Multi-View Differential Mixing and Graph-Guided Structural Region Selection for Cross-Modal Alignment

Linlin Ji, Li Liu

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 2 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
replace average pooling with the multi-view differential mixer for global aggregation (ablation)MG-Net · Flickr30K (Swin-Base-224)rSum: 510.2 -> 544.0Improved
use max pooling instead of average pooling for global aggregation (ablation)image-text matching · Flickr30K (Swin-Base-224)rSum: 510.2 -> 541.7Improved
add differential views (C=2) on top of the base view only (ablation)MDM · Flickr30K (Swin-Base-224)rSum: 540.8 -> 544.0Improved
increase differential order from 2 to 3 (ablation)MDM · Flickr30K (Swin-Base-224)rSum: 544.0 -> 543.5Hurt
add the graph-guided region selector (GSRS) to the MDM (ablation)MG-Net · Flickr30K (Swin-Base-224)rSum: 544.0 -> 547.2Improved
add text guidance to the GSRS node features (ablation)MG-Net · Flickr30K (Swin-Base-224)rSum: 545.1 -> 547.2Improved
MG-Net versus PICO on Flickr30K with Swin-384MG-Net · Flickr30K (Swin-Base-384)rSum: 548.2 -> 556.4Improved
MG-Net versus PICO on MS-COCO 1K with ViT-224MG-Net · MS-COCO 1K (ViT-Base-224)rSum: 527.9 -> 528.1Improved
MG-Net versus PICO on MS-COCO 1K text-to-image retrievalMG-Net · MS-COCO 1K (ViT-Base-224)text-to-image R@5: 91.6 -> 90.8Hurt
MG-Net versus PICO on MS-COCO 5K image-to-text R@1 with Swin-224MG-Net · MS-COCO 5K (Swin-Base-224)image-to-text R@1: 64.6 -> 67.9Improved

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