AI Paper Atlas

Research map / Optimization / Optimizers

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

Jin Gao, Weiming Hu, Yan Lu

CVPR 2020 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 22 citations (OpenAlex)

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 recursive LSE-aided online learning instead of RT-MDNet's original online updateRT-MDNet · OTB-2015AUC: absolute gains around 1.0%Improved
replace recursive LSE-aided MBSGD with original MBSGD while retaining only recent short-term memory (ablation)RLS-RTMDNet · OTB-2015AUCHurt
use recursive LSE-aided online learning instead of RT-MDNet's original updateRT-MDNet · VOT2016EAO: 0.302 -> 0.338Improved
use recursive LSE-aided online learning instead of RT-MDNet's original updateRT-MDNet · VOT2017EAO: 0.223 -> 0.256Improved
use recursive LSE-aided online learning instead of RT-MDNet's original updateRT-MDNet · UAV123AUC: 0.514 -> 0.516No clear effect
use recursive LSE-aided online learning instead of RT-MDNet's original updateRT-MDNet · UAV123OP0.75: 0.310 -> 0.320Improved
retain historical training information through recursive LSE-aided updates rather than relying on recent-only memoryRT-MDNet · UAV123, Full OcclusionAUC: 0.299 -> 0.316Improved

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