AI Paper Atlas

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

Modality-missing RGBT Tracking: Invertible Prompt Learning and High-quality Benchmarks

Andong Lu, Chenglong Li, J. Zhao, Jin Tang, Bin Luo

IJCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 33 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
use IPer in all layers instead of the first layer only (ablation)IPL · RGBT234-MissPR: 80.6 -> 82.0Improved
use IPer in all layers instead of the first layer only (ablation)IPL · LasHeR245-MissPR: 59.7 -> 61.7Improved
use invertible prompter instead of LoRA (ablation)IPL · RGBT234-MissPR: 79.1 -> 82.0Improved
use invertible prompter instead of LoRA (ablation)IPL · LasHeR245-MissPR: 59.1 -> 61.7Improved
add task alignment loss (ablation)IPL · RGBT234-MissPR: 80.3 -> 82.0Improved
add task alignment loss (ablation)IPL · LasHeR245-MissPR: 60.2 -> 61.7Improved
add IPer and TA over Copy baseline (ablation)Base w/ Copy · RGBT234-MissPR: 74.8 -> 82.0Improved
use concatenation fusion instead of summation (ablation)baseline tracker · RGBT234-MissPR: 75.4 -> 77.2Improved
use Transformer fusion instead of concatenation (ablation)baseline tracker · RGBT234-MissPR: 77.2 -> 74.8Hurt
use shared-specific extractor instead of shared extractor (ablation)baseline tracker · RGBT234-MissPR: 74.8 -> 75.4Improved
add shared-specific architecture (no IPer) in complete modality (ablation)Base · RGBT234PR: 86.4 -> 88.3Improved
train with missing-modality data (ablation)TBSI · RGBT234-MissPR: 76.1 -> 77.7Improved

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