AI Paper Atlas

Research map / Detection and segmentation / Tracking

Hedged Deep Tracking

CVPR 2016 · Detection and segmentation › Tracking · approach: Siamese network tracking · 741 citations (OpenAlex)

Check 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 convolutional-layer trackers with adaptive Hedge rather than using standard Hedge (ablation)HDT · OTB-50tracking performanceHelped
Use only one convolutional-layer tracker instead of hedging trackers from six layers (ablation)HDT · OTB-50tracking performanceHurt
Use features from progressively deeper convolutional layers (ablation)single-layer VGG trackers · OTB-50tracking performanceHelped
Use VGG-10 features alone rather than a hand-crafted-feature tracker (ablation)VGG-10 · OTB-50tracking performanceHurt
Combine early-layer spatial details with later-layer semantic featuresHDT · low-resolution sequencestracking performanceHelped
Limit target search to the local image region instead of searching the whole frameHDT · out-of-view challengetracking robustnessHurt

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