AI Paper Atlas

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

RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation

Hao Li, Yuhao Wang, Wenning Hao, Pingping Zhang, Dong Wang, Huchuan Lu

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 1 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-free context-aware reasoning module (CRM*) to baseline (ablation)Baseline tracker · RGBT234MPR: 87.9 -> 89.1Improved
add multi-modal transformer encoder with text on top of CRM* (ablation)Baseline + CRM* · RGBT234MPR: 89.1 -> 91.1Improved
use language-based CRM instead of text-free CRM* (ablation)MTE + CRM · RGBT234MPR: 91.1 -> 91.8Improved
add Adaptive Token Fusion (ATF) (ablation)MTE + CRM · RGBT234MPR: 91.8 -> 93.8Improved
apply ATF at four layers (6,12,18,24) instead of one (ablation)RAGTrack · RGBT234MSR: 67.9 -> 69.5Improved
use ATF instead of TBSI, BSI or DFM fusion (ablation)RAGTrack · RGBT234MSR: 68.2 -> 69.5 vs best alternative (BSI)Improved
use proposed augmentation instead of addition, Transformer or Mamba (ablation)CRM · RGBT234MSR: 69.0 -> 69.5 vs best alternative (Transformer)Improved
increase reasoning tokens from 1 to 4 (ablation)CRM · RGBT234MPR: 93.8 -> 93.2Hurt
add 2 learnable tokens to the text prefix instead of 0 (ablation)MTE · RGBT234MPR: 92.8 -> 93.8Improved
increase learnable tokens from 2 to 4 (ablation)MTE · RGBT234MSR: 69.5 -> 68.7Hurt
use all four attention scores for token selection instead of one (ablation)ATF · RGBT234MPR: 92.0 -> 93.8Improved
set retention ratio to 85% instead of lower or higher values (ablation)ATF · RGBT234MPRImproved

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