AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning Attribute-Specific Representations for Visual Tracking

Yuankai Qi, Shengping Zhang, Weigang Zhang, Li Su, Qingming Huang, Ming-Hsuan Yang

AAAI 2019 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 45 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
train attribute branches separately then ensemble layers (two-stage) instead of end-to-end (ablation)ANT · OTB100precision: 88.6 -> 90.5Improved
two-stage training instead of end-to-end (ablation)ANT · OTB100AUC: 65.8 -> 67Improved
use the matching attribute branch rather than the illumination branch (ablation)ANT branches · VOT video D (CarScale, scale)average success rate: 41.4 -> 62.2Improved
use the matching camera-motion branch rather than illumination branch (ablation)ANT branches · VOT video E (Basketball, camera)average success rate: 56.8 -> 70.6Improved
use the matching branch on occlusion video (ablation)ANT branches · VOT video C (Tiger2, occlusion)average success rate: 54.0 vs 52.2-52.9Mixed
ANT vs strongest baselines on OTB100ANT · OTB100precision: gap to ECO 0.3%Mixed
ANT vs MDNet on UAV-TrafficANT · UAV-Trafficprecision: 4.5% higher than MDNetImproved

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