AI Paper Atlas

Research map / Video / Video segmentation and tracking

VideoMatch: Matching based Video Object Segmentation

Yuan-Ting Hu, Jia-Bin Huang, Alexander G. Schwing

ECCV 2018 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 274 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 outlier removal (ablation)VideoMatch without online update · DAVIS-16 valmIoU: 0.792 -> 0.805Improved
add online background feature update (ablation)VideoMatch with outlier removal · DAVIS-16 valmIoU: 0.805 -> 0.809Improved
add online foreground feature update (ablation)VideoMatch with outlier removal and BG update · DAVIS-16 valmIoU: 0.809 -> 0.810Improved
use soft matching with top K=20 instead of hard matching K=1 (ablation)VideoMatch soft matching layer · DAVIS-16 valmIoU: 0.753 -> 0.792Improved
use top K=20 instead of averaging over all matches (ablation)VideoMatch soft matching layer · DAVIS-16 valmIoU: 0.636 -> 0.792Improved
add background matching to foreground matching (ablation)VideoMatch · DAVIS-16 valmIoU: 0.527 -> 0.792Improved
add online fine-tuning on first frame (ablation)VideoMatch · DAVIS-17 valmIoU: 0.565 -> 0.614Improved
add online fine-tuning on first frame (ablation)VideoMatch · DAVIS-17 valspeed (s per frame): 0.35 -> 2.62Hurt

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