AI Paper Atlas

Research map / Video / Video segmentation and tracking

SCOTCH and SODA: A Transformer Video Shadow Detection Framework

CVPR 2023 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 31 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 SODA instead of trajectory attention (ablation)MiT video shadow detector · ViShaBER: 12.35 -> 10.55Helped
add SODA to the MiT baseline (ablation)MiT video shadow detector · ViShaBER: 13.18 -> 10.55Helped
add trajectory attention to the MiT baseline (ablation)MiT video shadow detector · ViShaBER: 13.18 -> 12.35Helped
add SCOTCH shadow-level contrastive loss (ablation)MiT video shadow detector · ViShaBER: 13.18 -> 12.02Helped
add image-level contrastive loss (ablation)MiT video shadow detector · ViShaBER: 13.18 -> 12.85Helped
replace image-level contrast with SCOTCH shadow-level contrast (ablation)MiT video shadow detector · ViShaBER: 12.85 -> 12.02Helped
add both SODA and SCOTCH (ablation)MiT video shadow detector · ViShaBER: 13.18 -> 9.066Helped
use SCOTCH and SODA rather than SC-CorViSha video shadow detection · ViShaIoU: 0.615 -> 0.640Helped

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