Research map / Video / Video segmentation and tracking
MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions
Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Chen Change Loy
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add temporal context module (global attention) to image-based VLT (ablation) | VLT · MeViS val | J&F: 27.8 -> 35.5 | Improved |
| add temporal context module to ReferFormer (ablation) | ReferFormer · MeViS val | J&F: 31.0 -> 36.3 | Improved |
| add temporal context module (ablation) | VLT · Refer-Youtube-VOS | J&F: 63.1 -> 62.7 | No clear effect |
| add temporal context module (ablation) | ReferFormer · DAVIS17-RVOS | J&F: 60.2 -> 59.9 | No clear effect |
| add motion perception (inter-frame self-attention on object embeddings) (ablation) | LMPM · MeViS val | J&F: 31.0 -> 36.3 | Improved |
| add threshold-based matching for multi-object expressions (ablation) | LMPM · MeViS val | J&F: 36.3 -> 37.2 | Improved |
| sample 5 random frames instead of 1 frame (video vs image-based model) | VLT vs ReferFormer · MeViS val | J&F: 27.8 -> 31.0 | Improved |
| train on image referring datasets instead of video referring data | VLT · MeViS val | J&F: 27.8 -> 22.5 | Hurt |
Closest papers by meaning
- MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation (TPAMI 2025 · similarity 0.96)
- Decoupled Motion Expression Video Segmentation (CVPR 2025 · similarity 0.90)
- Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation (CVPR 2026 · similarity 0.89)
- Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation (CVPR 2024 · similarity 0.87)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.86)
- Segment Any Motion in Videos (CVPR 2025 · similarity 0.86)
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.
