AI Paper Atlas

Research map / Video / Video segmentation and tracking

Towards Open-Vocabulary Video Instance Segmentation

Haochen Wang, Cilin Yan, Shuai Wang, Xiaolong Jiang, Xu Tang, Yao Hu, Weidi Xie, Efstratios Gavves

ICCV 2023 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 50 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
Use end-to-end video queries (OV2Seg) instead of propose-reduce-association baselinesOV2Seg · LV-VIS val novelAP novel: 5.4 -> 11.9 (vs Detic-XMem, R50)Improved
Use class-independent queries instead of class-dependent queries (ablation)OV2Seg · LVIS / LV-VIS(O) image-levelfps: 0.10 -> 21.6 fps at comparable AP novel (17.4 vs 17.5)Improved
Add memory update (alpha=0.7) to query association (ablation)OV2Seg · YouTube-VIS 2019mAP: 23.7 -> 27.2Improved
Vary memory update factor alpha between 0.3 and 0.8 (ablation)OV2Seg · YouTube-VIS 2019, LV-VIS valmAPNo clear effect
Classify with memory queries instead of averaging per-frame scores (ablation)OV2Seg · LV-VIS valAP novel: 11.3 -> 11.9Improved
Use OV2Seg instead of Detic at image levelOV2Seg · LVISAP: 30.2 -> 25.4 AP (R50)Hurt
Use OV2Seg with SwinB backbone instead of R50OV2Seg · LV-VIS valAP: 14.2 -> 21.1Improved

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