AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines

Yuan-Ting Hu, Hong-Shuo Chen, Kexin Hui, Jia-Bin Huang, Alexander G. Schwing

CVPR 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 90 citations (OpenAlex)

Check 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
Pretrain VideoMatch using SAIL-VOS synthetic video dataVideoMatch · DAVIS16 validation with limited DAVIS training dataIoU: 0.55 -> 0.74; 0.66 -> 0.77; 0.73 -> 0.78; 0.74 -> 0.78Improved
Pretrain VideoMatch using SAIL-VOS synthetic video dataVideoMatch · DAVIS16 validation with 50% and 100% DAVIS training dataIoU: 0.78 -> 0.78; 0.81 -> 0.79Mixed
Jointly predict modal and amodal masks instead of predicting amodal masks aloneMaskAmodal · SAIL-VOS validation, class-agnostic amodalAP50: 40.4 -> 40.8Improved
Jointly predict modal and amodal masks instead of predicting amodal masks aloneMaskAmodal · SAIL-VOS validation, class-agnostic amodalAP: 26.6 -> 26.4Hurt
Use temporal context from adjacent frames for amodal segmentationFrame-based amodal segmentation · SAIL-VOSamodal segmentation performanceMixed

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