AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning Target Candidate Association To Keep Track of What Not To Track

Christoph Mayer, Martin Danelljan, Danda Pani Paudel, Luc Van Gool

ICCV 2021 · Detection and segmentation › Tracking · approach: Siamese network tracking · 413 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 target candidate association network (ablation)SuperDiMP with memory confidence and search area adaptation · LaSOTAUC (%): 65.8 -> 67.1Improved
add target candidate association network (ablation)SuperDiMP with memory confidence and search area adaptation · NFSAUC (%): 65.2 -> 66.4Improved
add target candidate association network (ablation)SuperDiMP with memory confidence and search area adaptation · UAV123AUC (%): 69.1 -> 69.7Improved
add memory sample confidence (ablation)SuperDiMP · LaSOTAUC (%): 63.5 -> 65.0Improved
add memory sample confidence (ablation)SuperDiMP · NFS / UAV123AUC (%): 64.4 -> 64.7 (NFS); 68.2 -> 68.0 (UAV123)No clear effect
add search area adaptation (larger area and rescaling) (ablation)SuperDiMP with memory confidence · LaSOTAUC (%): 65.0 -> 65.8Improved
add larger search area only (ablation)SuperDiMP with memory confidence · LaSOTAUC (%): 65.0 -> 65.5Improved
add search area rescaling only (ablation)SuperDiMP with memory confidence · LaSOTAUC (%): 65.0 -> 65.8Improved
add partially supervised loss only for association training (ablation)TCA · LaSOTAUC (%): 65.8 -> 66.0Improved
add self-supervised loss only for association training (ablation)TCA · LaSOTAUC (%): 65.8 -> 66.9Improved
add data-mining when training with combined loss (ablation)TCA · LaSOTAUC (%): 66.8 -> 67.1Improved
use sample confidence for replacement, then for online learning, then threshold 0.5 (ablation)memory management · LaSOTAUC (%): 63.5 -> 64.1 -> 64.6 -> 65.0Improved

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