AI Paper Atlas

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

TriSim: Tri-Dimensional Similarity Modeling with Extreme Value Theory for False-Negative Mitigation in Remote Sensing Image-Text Retrieval

Chengyu Zheng, Hanzhang Lu, Jie Nie, Shan Du

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval

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 ETSM (EVT-guided 3D similarity FNS identification) to the baseline (ablation)TriSim · RSITMDmR: 47.96 -> 49.86Improved
add IGDO (intra-modal saliency gain matrix) (ablation)TriSim · RSITMDmR: 49.86 -> 51.35Improved
use 3D similarity thresholding per quadrant instead of single cross-modal threshold (ablation)FNS detection · RSITMDmR: 48.54 -> 49.16Improved
use Mahalanobis plus EVT filtering instead of per-quadrant thresholds (ablation)FNS detection · RSITMDmR: 49.16 -> 51.35Improved
replace single cross-modal threshold with Mahalanobis plus EVT filtering (ablation)FNS detection · RSITMDmR: 48.54 -> 51.35Improved
add IGDO on text retrieval (ablation)TriSim · RSITMDT->I R@1: 24.61 -> 26.95Improved
add IGDO on image retrieval R@1 (ablation)TriSim · RSITMDI->T R@1: 27.66 -> 26.55Hurt
TriSim vs best prior method on RSICDTriSim · RSICDmR: 36.99 -> 37.55Improved
TriSim vs best prior method on RSITMDTriSim · RSITMDmR: 50.22 -> 51.35Improved
vary quantile qu before last layer (0.8, 0.9, 0.95) (ablation)ETSM · RSITMDmR: peak 51.35 at 0.9Mixed
vary beta before last layer (0.05, 0.1, 0.2) (ablation)ETSM · RSITMDmR: peak 51.35 at 0.1Mixed
vary pg before last layer (0.05, 0.1 and higher) (ablation)ETSM · RSITMDmR: peak 51.35 at 0.1Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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