AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning Regression and Verification Networks for Robust Long-term Tracking

Yunhua Zhang, Lijun Wang, Dong Wang, Jinqing Qi, Huchuan Lu

IJCV 2021 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 103 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 verification network to regression network (ablation)regression tracker · VOT2018 LTB35F-score: 0.525 -> 0.610Improved
add concatenation of template feature in fusion (ablation)object-aware fusion · VOT2018 LTB35F-score: 0.582 -> 0.610Improved
add multiplication of search and template features in fusion (ablation)object-aware fusion · VOT2018 LTB35F-score: 0.442 -> 0.610Improved
use separate parameters for template and search branches instead of Siamese sharing (ablation)regression network · VOT2018 LTB35F-score: 0.497 -> 0.610Improved
add verification network (precision) (ablation)regression tracker · VOT2018 LTB35precision: 0.563 -> 0.634Improved
add verification network (recall) (ablation)regression tracker · VOT2018 LTB35recall: 0.493 -> 0.588Improved
combine regression and verification scores with image-wide re-detectionDaSiam_LT-style tracker · VOT2018 LTB35re-detection success: 0% -> 100%Improved
use fixed regression network plus online verification instead of SiamFC with random re-detectionSiamFC+R · OxUvAMaxGM: 0.454 -> 0.544Improved

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