AI Paper Atlas

Research map / Detection and segmentation / Tracking

Distractor-Aware Memory-Based Visual Object Tracking

Jovana Videnović, Matej Kristan, Alan Lukežič

IJCV 2026 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 3 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
skip memory updates when the predicted mask is empty (ablation)SAM2.1 · DiDitracking quality: 0.649 -> 0.665Improved
update memory every 5th frame instead of every frame (ablation)SAM2.1_PRES · DiDitracking quality: 0.665 -> 0.667No clear effect
add DRM updated only during reliable tracking (ablation)SAM2.1_Delta=5 · DiDitracking quality: 0.667 -> 0.672Improved
add DRM updated on distractor detection alone, without reliability check (ablation)SAM2.1_Delta=5 · DiDitracking quality: 0.667 -> 0.644Hurt
combine distractor detection and reliability condition for DRM updates (full DAM) (ablation)SAM2.1_Delta=5 · DiDitracking quality: 0.667 -> 0.694Improved
use connected components instead of a 3x3 median filter for noise removal (ablation)DAM4SAM · DiDitracking quality: 0.692 -> 0.694No clear effect
remove temporal encoding from DRM (ablation)DAM4SAM · DiDitracking quality: 0.669 -> 0.694Improved
always include the most recent frame in RAM (ablation)DAM4SAM · DiDitracking quality: 0.685 -> 0.694Improved
use 3 RAM and 3 DRM slots instead of 4 and 4 (ablation)DAM4SAM · VOT2022AO: 0.749 -> 0.792Improved
use 3 RAM and 3 DRM slots instead of 2 and 2 (ablation)DAM4SAM · VOT2022AO: 0.781 -> 0.792Improved
vary theta_anc in 0.6-0.9 and theta_IoU in 0.5-0.8 (ablation)DAM4SAM · VOT2022AO: Theta_anc in [0.6, 0.9]; Theta_IoU in [0.5, 0.8]No clear effect
add distractor-aware memory to SAM2.1 Hiera-TSAM2.1-T · DiDitracking quality: 0.600 -> 0.642Improved

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