AI Paper Atlas

Research map / Video / Video-language understanding

WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking

Chunhui Zhang, Guanjie Huang, Li Liu, Shan Huang, Yinan Yang, Xiang Wan, Shiming Ge, Dacheng Tao

TPAMI 2022 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 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
use SATA instead of CVAT for annotationsemi-automatic annotation · annotation timemean time per box: 3.86 s -> 2.99 sImproved
use SATA instead of manual Labelmeannotation · annotation timemean time per box: 15.81 s -> 2.99 sImproved
add a refinement module (AlphaRefine) to DiMPDiMP · WebUAV-3M test setAUC: 0.364 -> 0.593Improved
use probabilistic regression (PrDiMP) in place of DiMPDiMP · WebUAV-3M test setAUC: 0.364 -> 0.514Improved
use handcrafted-feature MCCT versus deep ATOMtracker choice · WebUAV-3M test setAUC: 0.291 -> 0.440Improved
classic ECO versus recent ATOMtracker choice · WebUAV-3M test setAUC: 0.291 -> 0.450Improved
AlphaRefine versus second-best trackertracker choice · WebUAV-3M test setPre, nPre, AUC, cAUC, mAcc: 4.3%, 4.0%, 5.0%, 5.0% and 5.2%Improved
lightweight AlexNet-based SiamRPN vs deeper trackersspeed · WebUAV-3M test setFPS: 142.8@GPU vs 32.4@GPU (PrDiMP)Improved
retrain five trackers on WebUAV-3M training setSiamFC, SiamRPN, ATOM, GOTURN, MDNet · WebUAV-3M test setPre, nPre, AUC, cAUC, mAccImproved
increase adversarial perturbation iterationsmost trackers · adversarial examples subtestmAccNo clear effect
add adversarial examples to inputTransT and MDNet · adversarial examples subtestmAccHurt
decrease target size below 30all trackers · small targets subtestmAccHurt

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