atlas

Research map / Detection and segmentation / Tracking

Target-Aware Deep Tracking

CVPR 2019 · Detection and segmentation › Tracking · approach: Siamese network tracking · 451 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 regression-guided rather than random filter selection on Conv4-1 (ablation)Target-Aware Deep Tracking · OTB-2013AUC: +4.3%Helped
Use regression-guided rather than random filter selection on Conv4-1 (ablation)Target-Aware Deep Tracking · OTB-2015AUC: +4.4%Helped
Use regression-guided rather than random filter selection on Conv4-3 (ablation)Target-Aware Deep Tracking · OTB-2013AUC: +4.9%Helped
Use regression-guided rather than random filter selection on Conv4-3 (ablation)Target-Aware Deep Tracking · OTB-2015AUC: +3.4%Helped
Combine regression-guided features from Conv4-1 and Conv4-3 (ablation)Target-Aware Deep Tracking · OTB-2013AUC: +0.7%Helped
Combine regression-guided features from Conv4-1 and Conv4-3 (ablation)Target-Aware Deep Tracking · OTB-2015AUC: +0.7%Helped
Add ranking-guided scale-sensitive Conv4-1 features to the regression-guided feature combination (ablation)Target-Aware Deep Tracking · OTB-2013AUC: +1.8%Helped
Add ranking-guided scale-sensitive Conv4-1 features to the regression-guided feature combination (ablation)Target-Aware Deep Tracking · OTB-2015AUC: +1.6%Helped

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