AI Paper Atlas

Research map / Detection and segmentation / Tracking

GradNet: Gradient-Guided Network for Visual Object Tracking

Peixia Li, Boyu Chen, Wanli Ouyang, Dong Wang, Xiaoyun Yang, Huchuan Lu

ICCV 2019 · Detection and segmentation › Tracking · approach: Siamese network tracking · 351 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 template generalization training (one template across search regions from several videos) (ablation)GradNet · OTB-2015precision: 0.823 -> 0.861Improved
add template generalization training (ablation)GradNet · OTB-2015success (IOU): 0.615 -> 0.639Improved
add gradient-guided update branch on top of SiameseFC (full method vs baseline)SiameseFC · OTB-2015precision: 0.771 -> 0.861Improved
add template generalization and gradient application (vs two unshared branches) (ablation)GradNet · OTB-2015precision: 0.717 -> 0.861Improved
add online template update (ablation)GradNet · OTB-2015precision: 0.775 -> 0.861Improved
add online template update (ablation)GradNet · OTB-2015FPS: 85 -> 80Hurt
share parameters between sub-nets U1 and U2 (vs separate parameters) (ablation)GradNet · OTB-2015precision: 0.833 -> 0.861Improved
share parameters between sub-nets U1 and U2 (ablation)GradNet · OTB-2015success (IOU): 0.628 -> 0.639Improved
add gradient-guided template update to SiameseFCSiameseFC · VOT2017EAO: 0.182 -> 0.247Improved
add gradient-guided template update to SiameseFCSiameseFC · VOT2017robustness failures (R): 0.604 -> 0.375Improved
use GradNet versus SiamRPN trained on far more dataGradNet vs SiamRPN · VOT2017EAO: 0.247 vs 0.244No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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