AI Paper Atlas

Research map / Detection and segmentation / Tracking

Tracking Completion

Yao Sui, Guanghui Wang, Yafei Tang, Li Zhang

ECCV 2016 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 14 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
use matrix-completion tracker instead of best competing tracker LLRtracker · 20 video sequencestracking location error: 9.9 -> 5.8Improved
use proposed tracker instead of DSLtracker · 20 video sequencesprecision (delta=20): 0.91 -> 0.96Improved
use proposed tracker instead of DSLtracker · 20 video sequencessuccess rate (rho=0.5): 0.85 -> 0.86Improved
use proposed tracker instead of DSLtracker · 20 video sequencesoverlap rate: 0.70 -> 0.72Improved
add local observations to the global subspace matrix completion (ablation)tracker · 20 video sequencesoverlap rateImproved
observe about 70% of pixels per frame rather than fewer or more (ablation)tracker · 20 video sequenceslocation error and overlap rateImproved
observe too few pixels (ablation)tracker · 20 video sequencestracking accuracyHurt
observe too many pixels (ablation)tracker · 20 video sequencestracking accuracyHurt

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