AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-supervised Amodal Video Object Segmentation

Jian Yao, Yuxin Hong, Chiyu Wang, Tianjun Xiao, Tong He, Francesco Locatello, David Wipf, Yanwei Fu, Zheng Zhang

NeurIPS 2022 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 4 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 test-time adaptation (ablation)SaVos · FISHBOWL unseen fish, overallmean-IoU (occluded): 0.5905 -> 0.6886Improved
add test-time adaptationSelf-Deocclusion · FISHBOWL unseen fish, overallmean-IoU (occluded): 0.5859 -> 0.5971Improved
add test-time adaptation (ablation)SaVos · FISHBOWL unseen fish, overallmean-IoU (full): 0.8428 -> 0.8663Improved
add test-time adaptation on unseen BigFishB (ablation)SaVos · FISHBOWL BigFishBmean-IoU (occluded): 0.4978 -> 0.6230Improved
add test-time adaptation on unseen SmallFishASelf-Deocclusion · FISHBOWL SmallFishAmean-IoU (occluded): 0.4757 -> 0.4629Hurt
add test-time adaptation to KINS-Video-Car for FISHBOWL-trained model (ablation)SaVos · KINS-Video-Carmean-IoU (occluded): 0.0994 -> 0.2976Improved
add test-time adaptation to KINS-Video-Car for FISHBOWL-trained modelSelf-Deocclusion · KINS-Video-Carmean-IoU (occluded): 0.0658 -> 0.0969Improved
replace Self-Deocclusion trained on KINS-Video-Car with SaVos trained on FISHBOWL plus adaptationSelf-Deocclusion · KINS-Video-Carmean-IoU (occluded): 0.1790 -> 0.2976Improved
use SaVos instead of Self-DeocclusionSelf-Deocclusion · Chewing Gummean-IoU (occluded): 0.3307 -> 0.8046Improved
use SaVos instead of Self-DeocclusionSelf-Deocclusion · FISHBOWLmean-IoU (occluded): 0.6502 -> 0.7155Improved
use SaVos instead of Self-DeocclusionSelf-Deocclusion · KINS-Video-Carmean-IoU (occluded): 0.1790 -> 0.3132Improved
use supervised oracle instead of SaVosSaVos · Chewing Gummean-IoU (occluded): 0.8046 vs 0.3321No clear effect

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