AI Paper Atlas

Research map / Detection and segmentation / Tracking

Saliency-Associated Object Tracking

Zikun Zhou, Wenjie Pei, Xin Li, Hongpeng Wang, Feng Zheng, Zhenyu He

ICCV 2021 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 152 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 pixel-to-pixel similarity maps (ablation)base model · OTB2015AUC: 0.651 -> 0.687Improved
add pixel-to-pixel similarity maps (ablation)base model · NFS30AUC: 0.597 -> 0.625Improved
add association modeling between matched local parts (ablation)PPFM · OTB2015AUC: 0.687 -> 0.701Improved
add association modeling between matched local parts (ablation)PPFM · NFS30AUC: 0.625 -> 0.641Improved
add saliency mining to select discriminative parts (ablation)PAM · OTB2015AUC: 0.701 -> 0.714Improved
add saliency mining to select discriminative parts (ablation)PAM · NFS30AUC: 0.641 -> 0.656Improved
add saliency mining to select discriminative parts (ablation)PAM · OTB2015precision: 0.909 -> 0.926Improved
use saliency mining and association instead of depth-wise correlation (ablation)SAOT · OTB2015AUC: 0.691 -> 0.714Improved
use saliency mining and association instead of pixel-to-global correlation (ablation)SAOT · OTB2015AUC: 0.693 -> 0.714Improved
use saliency mining and association instead of depth-wise correlation (ablation)SAOT · NFS30AUC: 0.617 -> 0.656Improved
use saliency mining and association instead of pixel-to-global correlation (ablation)SAOT · NFS30AUC: 0.619 -> 0.656Improved
part-based saliency tracking instead of holistic tracking with same online filter (DiMP)SAOT · OTB2015AUC: 2.8%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