AI Paper Atlas

Research map / Video / Video segmentation and tracking

Unsupervised Learning From Video to Detect Foreground Objects in Single Images

Ioana Croitoru, Simion-Vlad Bogolin, Marius Leordeanu

ICCV 2017 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 58 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
replace VideoPCA teacher with trained student CNNunsupervised foreground detector · ImageNet VID valmax F-measure: 41.83 -> 51.17Improved
add skip connections and HSV/derivative input channels (refined model) (ablation)student CNN · ImageNet VID valmax F-measure: 51.17 -> 52.51Improved
add 10% soft-mask selection (ablation)refined student CNN · ImageNet VID valmax F-measure: 52.51 -> 53.82Improved
keep only top 5% of masks instead of all (ablation)refined student CNN · ImageNet VID valmax F-measure: 52.51 -> 53.20Improved
keep top 30% of masks (ablation)refined student CNN · ImageNet VID valmax F-measure: 52.51 -> 53.67Improved
select 10% instead of 5% of masks (ablation)refined student CNN · ImageNet VID valmax F-measure: 53.20 -> 53.82Improved
add unlabeled YTO videos to training (ablation)baseline student CNN · ImageNet VID valmax F-measure: 51.17 -> 51.9Improved
add unlabeled YTO videos to training (ablation)refined student, 10% selection · ImageNet VID valmax F-measure: 53.82 -> 54.53Improved
add YTO videos to training (ablation)student CNN · Object Discovery CorLoc (3 classes avg)CorLoc: 86.04 -> 85.83No clear effect
add YTO videos to training (ablation)student CNN · Object Discovery segmentationmean J: 61.25 -> 62.33Improved
add YTO videos to training (ablation)student CNN · YouTube Objects v1CorLoc avg: 56.1 -> 61.6Improved
add skip connections (ablation)student CNN · ImageNet VID valperformance: 1%Improved

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