AI Paper Atlas

Research map / Detection and segmentation / Tracking

Global Dilated Attention and Target Focusing Network for Robust Tracking

AAAI 2023 · Detection and segmentation › Tracking · approach: Siamese network tracking · 14 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
replace self attention with GDA (ablation)GdaTFT · OTB100Precision: 88.3 -> 89.5Helped
replace feature fusion with TFN (ablation)GdaTFT · OTB100Precision: 88.4 -> 89.5Helped
combine GDA and TFN rather than use neither (ablation)GdaTFT · OTB100Success: 67.5 -> 70.4Helped
combine GDA and TFN rather than use neither (ablation)GdaTFT · OTB100Precision: 87.4 -> 90.6Helped
add GDA instead of self attention (ablation)GdaTFT · OTB100Precision: 88.3 -> 89.5Helped
add TFN instead of feature fusion (ablation)GdaTFT · OTB100Success: 68.6 -> 69.2Helped
use GdaTFTGdaTFT · LaSOTAUC: 64.9 -> 64.3Hurt
use GdaTFTGdaTFT · TrackingNetAUC: 81.4 -> 77.8Hurt
use GdaTFTGdaTFT · GOT-10kAO: 67.1 -> 65.0Hurt
use GdaTFTGdaTFT · GOT-10kSR0.5: 76.8 -> 77.8Helped

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