AI Paper Atlas

Research map / Detection and segmentation / Tracking

Non-Rigid Object Tracking via Deformable Patches Using Shape-Preserved KCF and Level Sets

Xin Sun, Ngai-Man Cheung, Hongxun Yao, Yiluan Guo

ICCV 2017 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 22 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 deformable level-set patches instead of fixed rectangular patches (RPT)patch-based KCF tracker · VOT2014 (25 sequences)correctly tracked frames (%): 65.4868 -> 71.0828Improved
use deformable level-set patches instead of fixed rectangular patches (RPT)patch-based KCF tracker · VOT2016 (60 sequences)correctly tracked frames (%): 54.0174 -> 56.7567Improved
use weighted local patches instead of a single global boosting model with level sets (SLSM)contour tracker · VOT2014 (25 sequences)correctly tracked frames (%): 56.4132 -> 71.0828Improved
use weighted local patches instead of a single global boosting model with level sets (SLSM)contour tracker · VOT2016 (60 sequences)correctly tracked frames (%): 47.8365 -> 56.7567Improved
use local patch models instead of HoughTrack global modelcontour tracker · VOT2014 (25 sequences)correctly tracked frames (%): 51.7184 -> 71.0828Improved
use deformable patches instead of distribution field trackerbounding box tracker · VOT2016 (60 sequences)correctly tracked frames (%): 42.0626 -> 56.7567Improved
use deformable patches versus PixelTrackbounding box tracker · VOT2016 (60 sequences)correctly tracked frames (%): 40.3302 -> 56.7567Improved
proposed tracker versus all compared trackers per sequenceproposed tracker · VOT2014 sequencescorrectly tracked frames (%): 13 out of 25Mixed
proposed versus RPT on davidproposed tracker · VOT2014 davidcorrectly tracked frames (%): 100 -> 78.57Hurt
proposed versus RPT on trellisproposed tracker · VOT2014 trelliscorrectly tracked frames (%): 100 -> 39.72Hurt
proposed versus RPT on divingproposed tracker · VOT2014 divingcorrectly tracked frames (%): 15.98 -> 100Improved
proposed versus RPT on joggingproposed tracker · VOT2014 joggingcorrectly tracked frames (%): 22.48 -> 100Improved

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