AI Paper Atlas

Research map / Detection and segmentation / Tracking

Discriminative Scale Space Tracking

Martin Danelljan, Gustav Hager, Fahad Shahbaz Khan, Michael Felsberg

TPAMI 2016 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 1,323 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 a separate scale filter (DSST) to the translation DCF (ablation)translation DCF tracker · OTB-50Mean OP (%): 57.7 -> 67.7Improved
add the scale filter to the translation DCF (ablation)translation DCF tracker · OTB-50AUC (%): 49.5 -> 6.6% gainImproved
add the scale filter to the translation DCF (ablation)translation DCF tracker · VOT 2014Final rank: 3.31 -> 2.80Improved
add the scale filter to the translation DCF (ablation)translation DCF tracker · VOT 2014Average failures: 1.48 -> 1.16Improved
use separate 1D scale filter instead of joint scale space filterDSST · OTB-50Mean FPS: 1.46 -> 25.4Improved
use separate scale filter instead of joint scale space filterDSST · OTB-50Mean OP (%): 63.2 -> 67.7Improved
use separate scale filter instead of multi-resolution translation filterDSST · OTB-50Mean OP (%): 65.2 -> 67.7Improved
add iterative refinement to joint scale space filterJoint DCF · OTB-50Mean OP (%): 63.2 -> 64.1Improved
add PCA dimensionality reduction, faster features and larger search space (fDSST)DSST · OTB-50Mean OP (%): 67.7 -> 74.3Improved
add PCA dimensionality reduction, faster features and larger search space (fDSST)DSST · OTB-50Mean FPS: 25.4 -> 54.3Improved
reduce translation filter subspace dimensions with PCA (ablation)fDSST · OTB-50AUC: 32 -> 18No clear effect
use fDSST with explicit scale filter instead of multi-feature SAMFSAMF · OTB-50Mean OP (%): 69.7 -> 74.3Improved

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