atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Cue Correlation Filters for Robust Visual Tracking

CVPR 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 490 citations (OpenAlex)

Read the paperCheck 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
combine multiple expert predictions with robustness-based expert selection (ablation)MCCT · OTB-2015DP (@20px): 87.1 -> 88.3Helped
add adaptive update based on expert divergence and PSR (ablation)MCCT · OTB-2015DP (@20px): 88.3 -> 91.4Helped
add adaptive update based on expert divergence and PSR (ablation)MCCT-H · OTB-2013DP (@20px): 83.5 -> 85.6Helped
replace the proposed reliability score with PSR-based sample reliability (ablation)MCCT · OTB-2013DP (@20px): 91.9 -> 90.9Hurt
replace the proposed reliability score with PSR-based sample reliability (ablation)MCCT-H · OTB-2015DP (@20px): 83.3 -> 82.7Hurt
use multiple experts and select the most robust prediction instead of relying on one expert (ablation)MCCT · OTB-2013DP (@20px): 89.7 -> 92.8Helped
use multiple experts and select the most robust prediction instead of relying on one expert (ablation)MCCT-H · OTB-2015DP (@20px): 79.2 -> 84.1Helped

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