AI Paper Atlas

Research map / Detection and segmentation / CNN features

Language As Queries for Referring Video Object Segmentation

Jiannan Wu, Yi Jiang, Peize Sun, Zehuan Yuan, Ping Luo

CVPR 2022 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 168 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
Use ReferFormer rather than URVOS with ResNet-50Referring video object segmentation · Ref-Youtube-VOSJ&F: 47.2 -> 55.6Improved
Use ReferFormer rather than URVOS with ResNet-50Referring video object segmentation · Ref-DAVIS17J&F: 51.5 -> 58.5Improved
Use ReferFormer with Video-Swin-B rather than MTTR with Video-Swin-TReferring video object segmentation · A2D-SentencesmAP: 46.1 -> 55.0Improved
Use ReferFormer with Video-Swin-B rather than MTTR with Video-Swin-TReferring video object segmentation · JHMDB-SentencesmAP: 39.2 -> 43.7Improved
Add visual-language fusion (ablation)ReferFormer · Ref-Youtube-VOS (Video-Swin-T, trained from scratch)J: 53.0 -> 54.8Improved
Add relative coordinates to mask features (ablation)ReferFormer · Ref-Youtube-VOS (Video-Swin-T, trained from scratch)J: 53.7 -> 54.8Improved
Use 5 rather than 8 conditional queries (ablation)ReferFormer · Ref-Youtube-VOS (Video-Swin-T, trained from scratch)J&F: 55.3 -> 56.0Improved
Train with 5 rather than 1 frame per clip (ablation)ReferFormer · Ref-Youtube-VOS (Video-Swin-T, trained from scratch)J&F: 50.0 -> 56.0Improved
Include box and mask costs in label assignment (ablation)ReferFormer · Ref-Youtube-VOS (Video-Swin-T, trained from scratch)J&F: 55.2 -> 56.0; 54.5 -> 56.0Improved
Use class-agnostic rather than class-discriminative training (ablation)ReferFormer · Ref-Youtube-VOSJ&F: 53.9 -> 56.0Improved
Add CFBI post-processing to the model (ablation)ReferFormer with ResNet-50 · Ref-Youtube-VOSJ&F: 55.6 -> 59.4Improved
Add CFBI post-processing to the model (ablation)ReferFormer with Swin-L · Ref-Youtube-VOSJ&F: 62.4 -> 63.3Improved

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