AI Paper Atlas

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

Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T Tracking

Chenglong Li, Chengli Zhu, Yan Huang, Jin Tang, Liang Wang

ECCV 2018 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 162 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 soft cross-modal consistency (ablation)Ours · GTOTPR: 78.7 -> 82.7Improved
add soft cross-modal consistency (ablation)Ours · GTOTSR: 61.2 -> 64.3Improved
add optimal query learning (ablation)Ours · GTOTPR: 78.0 -> 82.7Improved
add optimal query learning (ablation)Ours · GTOTSR: 63.1 -> 64.3Improved
add patch weights to feature representation (ablation)Ours · GTOTPR: 71.1 -> 82.7Improved
add patch weights to feature representation (ablation)Ours · GTOTSR: 57.6 -> 64.3Improved
l1-norm instead of l2-norm for optimal query learning (ablation)Ours · GTOTheatmap qualityImproved
compare with deep-feature tracker ECOOurs · GTOTPR/SR: 5.0%/1.2% over ECOImproved
compare with RGB-T tracker SGTOurs · RGBT210PR/SR: 1.9%/3.3% over SGTImproved
vary beta from 0.002 to 0.0002 (ablation)Ours · GTOTSR: 0.643 -> 0.615Hurt

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