AI Paper Atlas

Research map / Video / Video segmentation and tracking

CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos

Yeong Jun Koh, Chang-Su Kim

ICCV 2017 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 16 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 intra-frame refinement (ablation)Preliminary classification baseline · YouTube-Objects averageIoU: 0.581 -> 0.638Improved
add inter-frame refinement (ablation)Baseline + Intra · YouTube-Objects averageIoU: 0.638 -> 0.661Improved
add segment track management (ablation)Baseline + Intra + Inter · YouTube-Objects averageIoU: 0.661 -> 0.672Improved
use CDTS instead of offline MOS method [34]MOS [34] · YouTube-Objects averageIoU: 0.581 -> 0.672Improved
use CDTS instead of offline MOS method [42]MOS [42] · YouTube-Objects averageIoU: 0.524 -> 0.672Improved
use CDTS instead of MOS method [23]MOS [23] · YouTube-Objects averageIoU: 0.155 -> 0.672Improved
use CDTS instead of online MOS [32]MOS [32] · FBMS testF-measure: 0.672 -> 0.745Improved
use CDTS instead of MOS [23] on FBMSMOS [23] · FBMS testobjects with F-measure >= 0.75: 20/69 -> 30/69Improved

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