AI Paper Atlas

Research map / Detection and segmentation / Tracking

Video Annotation for Visual Tracking via Selection and Refinement

Kenan Dai, Jie Zhao, Lijun Wang, Dong Wang, Jianhua Li, Huchuan Lu, Xuesheng Qian, Xiaoyun Yang

ICCV 2021 · Detection and segmentation › Tracking · approach: Siamese network tracking · 9 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 forward/backward selection by T-Assess quality score (ablation)VASR (vs forward-only) · LaSOT train-set annotation accuracymIoU / Acc@0.7: 0.834 -> 0.845; 90.7% -> 87.6%Mixed
add failure detection to selection (ablation)VASR selection · LaSOT train-set annotation accuracyAcc@0.7: 87.6% -> 91.1%Improved
add appearance-only refinement (ablation)VASR · LaSOT train-set annotation accuracymIoU: 0.851 -> 0.845Hurt
add handcrafted geometric interpolation to visual refinement vs no refinement (ablation)VASR · LaSOT train-set annotation accuracymIoU: 0.851 -> 0.853No clear effect
add learned visual-geometry refinement (VG-Refine Net) (ablation)VASR · LaSOT train-set annotation accuracymIoU: 0.851 -> 0.865Improved
use LSTM instead of fully connected layers (ablation)VASR · LaSOT train-set annotation accuracymIoU: 0.859 -> 0.865Improved
use LSTM instead of fully connected layers (ablation)VASR · LaSOT train-set annotation accuracyErr Rate: 0.34% -> 0.25%Improved
use separate sequential predictors for forward and backward tracking (ablation)T-Assess Net · LaSOTannotation accuracyImproved
use rectified accumulation aggregation instead of max/average pooling or summation (ablation)VG-Refine Net training · LaSOTannotation accuracyImproved
train SiamFC++ on VASR instead of original TrackingNet annotationsSiamFC++ · TrackingNet testSuccess: 0.754 -> 0.770Improved
train PrDiMP on VASR instead of original TrackingNet annotationsPrDiMP · GOT10K testAO: 0.576 -> 0.589Improved
train SiamFC++ on VASR instead of original TrackingNet annotationsSiamFC++ · GOT10K testSR0.75: 0.363 -> 0.442Improved

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