AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Shadow Correspondence for Video Shadow Detection

Xinpeng Ding, Jingwen Yang, Xiaowei Hu, Xiaomeng Li

ECCV 2022 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 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
add SC-Cor to DSD (ablation)DSD · ViShaBER: 19.89 -> 15.67Improved
add SC-Cor to DSD (ablation)DSD · ViShaTS: 74.68 -> 77.09Improved
add brightness shift to DSD (ablation)DSD · ViShaTS: 74.68 -> 74.92No clear effect
add brightness shift to DSD (ablation)DSD · ViShaBER: 19.89 -> 16.82Improved
add brightness shift to SC-Cor (ablation)SC-Cor · ViShaAVG: 67.00 -> 68.22Improved
add bidirectional correspondence (ablation)SC-Cor · ViShaAVG: 67.17 -> 68.22Improved
add non-shadow regularization to shadow-only (ablation)SC-Cor · ViShaAVG: 67.04 -> 68.22Improved
add shadow regularization to non-shadow-only (ablation)SC-Cor · ViShaAVG: 66.91 -> 68.22Improved
use 4 frames instead of 2 (ablation)SC-Cor · ViShaAVG: 68.01 -> 68.39Improved
increase frame interval from 1 to 7 (ablation)SC-Cor · ViShaTS: 76.94 -> 78.23Mixed
increase frame interval from 1 to 7 (ablation)SC-Cor · ViShaBER: 14.51 -> 15.64Mixed
plug SC-Cor into DSDDSD · ViShaAVG: 63.29 -> 68.22Improved

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