AI Paper Atlas

Research map / Detection and segmentation / Tracking

Online Metric-Weighted Linear Representations for Robust Visual Tracking

Xi Li, Chunhua Shen, Anthony Dick, Zhongfei Mark Zhang, Yueting Zhuang

TPAMI 2016 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 22 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 metric learning to the linear representation (ablation)tracker with raw pixel features · trace sequenceVOR: 0.07 -> 0.37Improved
add metric learning to the linear representation (ablation)tracker with raw pixel features · trace sequenceCLE: 139.30 -> 22.88Improved
add metric learning (ablation)tracker with weighted sampling · trace sequenceVOR: 0.51 -> 0.70Improved
add time-weighted reservoir sampling instead of uniform (ablation)metric-weighted tracker · trace sequenceVOR: 0.61 -> 0.70Improved
add time-weighted reservoir sampling (ablation)metric-weighted tracker · trace sequenceCLE: 15.52 -> 8.65Improved
add time-weighted reservoir sampling (ablation)metric-weighted tracker · cubicle sequenceCLE: 4.31 -> 4.31No clear effect
use step-by-step eigendecomposition instead of none (ablation)metric learning · trace sequenceVOR: 0.70 -> 0.75Improved
use final eigendecomposition instead of none (ablation)metric learning · trace sequenceVOR: 0.70 -> 0.52Hurt
add structured distance metric learning (Ours+S)Ours · trellis70 sequenceVOR: 0.78 -> 0.83Improved
add structured distance metric learning (Ours+S)Ours · B-Beam sequenceCLE: 4.68 -> 3.52Improved
use L1 representation instead of metric-weighted linear representationtracker with raw pixels · race sequenceCLE: 5.18 -> 160.79Hurt
increase sample buffer size (ablation)reservoir sampling · five video sequencesCLE and VORImproved

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