AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning Feature Embeddings for Discriminant Model based Tracking

Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu

ECCV 2020 · Detection and segmentation › Tracking · approach: Siamese network tracking · 100 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
use original shrinkage loss instead of mean square error loss (ablation)DCFST-18 · OTB2015mean AUC: 0.682 -> 0.698Improved
use the modified shrinkage loss instead of the original shrinkage loss (ablation)DCFST-18 · OTB2015mean AUC: 0.698 -> 0.709Improved
increase number of RoI samples N from 361 to 961 (ablation)DCFST-18 · OTB2015mean AUC: 0.692 -> 0.709Improved
increase number of RoI samples N from 961 to 1369 (ablation)DCFST-18 · OTB2015mean AUC: 0.709 -> 0.707No clear effect
increase number of RoI samples N from 361 to 961 (ablation)DCFST-18 · OTB2015mean FPS: 46 -> 35Hurt
learn feature embeddings with closed-form ridge regression solver (DCFST-18) versus ATOM baselineDCFST-18 · OTB2015mean overlap: 0.832 -> 0.872Improved
DCFST-18 versus ATOM baselineDCFST-18 · NFS (30 FPS)mean AUC: 0.584 -> 0.634Improved
DCFST-18 versus DiMP-18 (closed-form solver vs iterative solver)DCFST-18 · NFS (30 FPS)mean AUC: 0.610 -> 0.634Improved
DCFST-18 versus ATOM baselineDCFST-18 · GOT10k testsuccess rate at 0.50: 0.634 -> 0.716Improved
DCFST-50 versus DiMP-50DCFST-50 · GOT10k testsuccess rate at 0.50: 0.717 -> 0.753Mixed
DCFST-18 versus ATOM baselineDCFST-18 · TrackingNet testsuccess (AUC): 0.703 -> 0.739Improved
DCFST-50 versus DiMP-50DCFST-50 · TrackingNet testsuccess (AUC): 0.740 -> 0.752Improved

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