AI Paper Atlas

Research map / Detection and segmentation / Tracking

Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking

Heng Fan, Haibin Ling

ICCV 2017 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 332 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 the parallel verifier to the fDSST trackerfDSST · OTB2015distance precision rate: 72 -> 84.9Improved
add the parallel verifier to the fDSST trackerfDSST · OTB2015overlap success rate: 67.6 -> 77.6Improved
add the parallel verifier to the fDSST trackerfDSST · TC128distance precision rate: 57.5% -> 74.1%Improved
add the parallel verifier to the fDSST trackerfDSST · TC128overlap success rate: 43.5% -> 54.4%Improved
run tracking and verifying in two threads instead of one (ablation)PTAV · OTB2013speed (fps): 16 -> 27Improved
run tracking and verifying in two threads instead of one (ablation)PTAV · UAV20Lspeed (fps): 15 -> 25Improved
use fDSST instead of KCF as the tracker (ablation)PTAV · OTB2013distance precision rate: 80.4 -> 89.4Improved
use fDSST instead of KCF as the tracker (ablation)PTAV · OTB2015overlap success rate: 57.9 -> 77.6Improved
use fDSST instead of KCF as the tracker (ablation)PTAV · OTB2013speed (fps): 24 -> 27Improved
shorten verification interval from V=10 to V=5 (ablation)PTAV · OTB2013distance precision rate and speed: DPR 89.4 -> 89.7, speed 27 -> 23 fpsMixed
lengthen verification interval from V=10 to V=15 (ablation)PTAV · OTB2013distance precision rate and speed: DPR 89.4 -> 87.9, speed 27 -> 29 fpsMixed
PTAV versus deep tracker HCF on TC128PTAV · TC128distance precision rate: 70.5% -> 74.1%Improved

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