AI Paper Atlas

Research map / Detection and segmentation / Tracking

Unveiling the Power of Deep Tracking

Goutam Bhat, Joakim Johnander, Martin Danelljan, Fahad Shahbaz Khan, Michael Felsberg

ECCV 2018 · Detection and segmentation › Tracking · approach: Siamese network tracking · 515 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 data augmentation to deep feature model training (ablation)ResNet deep features · OTB-2015AUC: 56.2 -> 61.5Improved
add blur augmentation (ablation)deep features · OTB-2015AUC: gain of 4%Improved
add flip/blur/other augmentations (except shift) (ablation)deep features · OTB-2015AUC: over 1% improvementImproved
add data augmentation to shallow feature training (ablation)shallow features · OTB-2015AUC: all augmentation types lower tracking performanceHurt
widen the label function (sigma 1/12 -> 1/4) (ablation)deep features · OTB-2015AUC: 56.2 -> 60.5Improved
widen the label function (ablation)shallow features · OTB-2015AUC: inferior results with higher sigmaHurt
add wider label function on top of data augmentation (ablation)deep features · OTB-2015AUC: 61.5 -> 62.0Improved
use tailored training plus adaptive fusion instead of ECOtracker with ResNet-50 · NFSAUC: 45.7 -> 54.1Improved
use tailored training plus adaptive fusion instead of ECOtracker with ResNet-50 · OTB-EAUC: 74.3 -> 78.0Improved
use tailored training plus adaptive fusion instead of ECOtracker with VGG-M · OTB-EAUC: 74.8 -> 74.2No clear effect
replace fixed-weight sum fusion with adaptive fusiondeep+shallow tracker · NFS and OTB-Eaccuracy (OP 0.75) and robustness (OP 0.5)Improved
replace ECO with the proposed trackertracker · VOT2017EAO: 0.280 -> 0.378Improved

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