AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation

Daizong Liu, Shuangjie Xu, Xiao-Yang Liu, Zichuan Xu, Wei Wei, Pan Zhou

AAAI 2021 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 21 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 the motion model's predicted current-frame location instead of using the previous bounding box (ablation)STG-Net proposal selection · DAVIS2017 test-devG_M: 53.2 -> 54.1; improvement of 0.9Improved
Add spatial graph reconstruction from all same-object proposals (ablation)STG-Net · DAVIS2017 test-devG_M: 54.1 -> 58.4; improvement of 4.3Improved
Set spatial graph alpha to 0.7 rather than 0.5 (ablation)STG-Net spatial graph · DAVIS2017 test-devG_M: 58.4 -> 59.2; improvement of 0.8Improved
Set mask-selection lambda1 to 0.4 rather than 0.5 (ablation)STG-Net mask selection · DAVIS2017 test-devG_M: 59.2 -> 59.8; improvement of 0.6Improved
Add temporal graph retrieval of historic masks (ablation)STG-Net · DAVIS2017 test-devG_M: 59.8 -> 61.9; improvement of 2.1Improved
Use 2 spatial graph updates rather than 1 (ablation)STG-Net spatial graph · DAVIS2017 test-devG_M: 61.9 -> 63.1Improved
Increase spatial graph updates from 2 to 3 (ablation)STG-Net spatial graph · DAVIS2017 test-devG_M: 63.1 -> 62.3Hurt
Add online learning on the first-frame annotation (ablation)STG-Net · DAVIS2017 test-devG_M: 63.1 -> 64.3; improvement of 1.2Improved
Fine-tune on the augmented DAVIS2017 training set (ablation)STG-Net · DAVIS2017 test-devG_M: 64.3 -> 66.5; improvement of 2.2Improved
Add YouTube-VOS pretraining (ablation)STG-Net · DAVIS2017 test-devG_M: 66.5 -> 69.4; improvement of 2.9Improved
Use STG-Net rather than FEEL*Video object segmentation · DAVIS2017 test-devG_M: 57.8 -> 63.1; 5.3%Improved
Use STG-Net rather than AGSSVideo object segmentation · YouTube-VOS valG_M: 71.3 -> 73.0; 1.7%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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