AI Paper Atlas

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

Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space

Huan Kang, Hui Li, Tianyang Xu, Tao Zhou, Xiaojun Wu, Josef Kittler

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 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 text guidance during training and testing (ablation)TEDFusion · TNOSD: 43.68 -> 44.52Improved
add text features at training time with attribute-based inference rather than text-only training (ablation)TEDFusion · TNOSD: 43.91 -> 44.52Improved
add the attribute and text gating fusion module (ATGFM) (ablation)TEDFusion · TNOSD: 44.17 -> 44.52Improved
do text-image association in hyperbolic Poincare ball instead of Euclidean space (ablation)TEDFusion · TNOSD: 44.24 -> 44.52Improved
do text-image association in hyperbolic Poincare ball instead of Euclidean space (ablation)TEDFusion · TNOAG: 3.21 -> 3.88Improved
add the adaptive hyperbolic loss L_h (ablation)TEDFusion · TNOSD: 42.70 -> 44.52Improved
add the adaptive hyperbolic loss L_h (ablation)TEDFusion · TNOSF: 12.41 -> 10.90Hurt
increase curvature from c=0.5 to c=1.0 (ablation)TEDFusion · TNOSD: 43.19 -> 44.52Improved
increase curvature from c=0.7 to c=1.0 (ablation)TEDFusion · TNOSF: 9.58 -> 10.90Improved
use TEDFusion instead of Text-IFText-IF · RoadSceneSD: 46.70 -> 60.85Improved
use TEDFusion instead of Text-IFText-IF · TNOSF: 7.88 -> 10.90Improved
use TEDFusion instead of Text-IFText-IF · M3FD detectionmAP@0.5: 49.23 -> 57.37Improved

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