AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning the Model Update for Siamese Trackers

Lichao Zhang, Abel Gonzalez-Garcia, Joost van de Weijer, Martin Danelljan, Fahad Shahbaz Khan

ICCV 2019 · Detection and segmentation › Tracking · approach: Siamese network tracking · 483 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
replace linear update with UpdateNetSiamFC · VOT2018EAO: 0.188 -> 0.262Improved
add skip connection from the initial ground-truth template T_0 to UpdateNet (ablation)UpdateNet (K=1) · VOT2018EAO: 0.205 -> 0.250Improved
add skip connection from the current template T_i (ablation)UpdateNet (K=1) · VOT2018EAO: 0.205 -> 0.207No clear effect
add skip connection from the previous accumulated template (ablation)UpdateNet (K=1) · VOT2018EAO: 0.205 -> 0.214Improved
add multi-stage training (K=3 instead of K=1) (ablation)UpdateNet · VOT2018EAO: 0.250 -> 0.262Improved
replace offline learned weighted fusion with UpdateNet (ablation)SiamFC · VOT2018EAO: 0.198 -> 0.262Improved
replace linear update with UpdateNetDaSiamRPN · VOT2016EAO: 0.439 -> 0.481Improved
replace linear update with UpdateNetDaSiamRPN · VOT2016Robustness (R): 0.262 -> 0.206Improved
replace linear update with UpdateNetDaSiamRPN · VOT2016Accuracy (A): 0.619 -> 0.610Hurt
replace linear update with UpdateNetDaSiamRPN · TrackingNet testSuccess (%): 63.8 -> 67.7Improved
replace linear update with UpdateNetSiamFC · TrackingNet testPrecision (%): 53.3 -> 53.1No clear effect
replace linear update with UpdateNetSiamFC · TrackingNet testSuccess (%): 57.1 -> 58.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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