AI Paper Atlas

Research map / Detection and segmentation / Tracking

Deep Reinforcement Learning with Iterative Shift for Visual Tracking

Liangliang Ren, Xin Yuan, Jiwen Lu, Ming Yang, Jie Zhou

ECCV 2018 · Detection and segmentation › Tracking · approach: Siamese network tracking · 61 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 iterative shift and a two-action policy (continue, stop & update) (ablation)Shift · OTB-2015distance precision: 0.822 -> 0.887Improved
add iterative shift and a two-action policy (continue, stop & update) (ablation)Shift · OTB-2015overlap success AUC: 0.593 -> 0.651Improved
add restart and stop & ignore actions to the policy (ablation)Shift + IS · OTB-2015distance precision: 0.887 -> 0.909Improved
add restart and stop & ignore actions to the policy (ablation)Shift + IS · OTB-2015overlap success AUC: 0.651 -> 0.671Improved
add the full action set with iterative shift to the one-step shift baseline (ablation)Shift · OTB-2015distance precision: 0.822 -> 0.909Improved
adding actions slows the tracker (22 fps vs 10.2 fps for full DRL-IS) (ablation)Shift · OTB-2015speed (fps): 22 fps -> 10.2 fpsHurt
replace MDNet with DRL-IS (iterative shift) for speedMDNet · OTB-2015speed (fps): 2.1 fps -> 10.2 fpsImproved
replace ADNet with DRL-IS (joint motion and tracking status)ADNet · OTB-2015distance precision: 0.880 -> 0.909Improved
replace C-COT with DRL-ISC-COT · Temple-Color128distance precision: 0.781 -> 0.818Improved
replace MDNet with DRL-IS on deformation sequencesMDNet · OTB-2015 deformation (40 sequences)overlap success AUC: 0.614 -> 0.631Improved
replace MDNet N with DRL-IS, both initialized from ImageNetMDNet N · VOT-2016robustness rank: 5.75 -> 2.70Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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