AI Paper Atlas

Research map / Video / Video segmentation and tracking

Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation

Anwesa Choudhuri, Girish Chowdhary, Alexander G. Schwing

CVPR 2023 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 14 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
Propagate and repeatedly refine a single set of object queries across frames (ablation)Context-aware relative object queries · OVIS validationAP: 9.8 -> 25.8Improved
Use propagated queries rather than concatenating learned new-object queries with previous queries (ablation)Context-aware relative object queries · OVIS validationAP: 16.9 -> 25.8Improved
Use relative instead of absolute positional encodings (ablation)Context-aware relative object queries · KITTI-MOTS carHOTA: 70.4 -> 83.2Improved
Use relative instead of absolute positional encodings (ablation)Context-aware relative object queries · KITTI-MOTS pedestrianHOTA: 52.0 -> 64.1Improved
Increase temporal context length from T=1 to T=2 (ablation)Context-aware relative object queries with ResNet-50 · OVIS validationAP: 19.1 -> 25.8Improved
Increase temporal context length from T=1 to T=2 (ablation)Context-aware relative object queries with Swin-L · OVIS validationAP: 34.0 -> 38.2Improved
Increase temporal context length from T=2 to T=4 (ablation)Context-aware relative object queries with ResNet-50 · OVIS validationAP: 25.8 -> 25.8No clear effect
Use the proposed online query propagation method rather than VITAVideo instance segmentation · YouTube-VIS 2019 validationAP: 49.8 -> 46.7Hurt
Use the proposed online query propagation method rather than VITAVideo instance segmentation · YouTube-VIS 2021 validationAP: 45.7 -> 43.3Hurt
Use the proposed method rather than VPS-NetVideo panoptic segmentation · Cityscapes-VPSVPQ: 57.5 -> 63.0Improved

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