Research map / Video / Video segmentation and tracking
Learning Quality-Aware Dynamic Memory for Video Object Segmentation
Yong Liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, Yujiu Yang
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 Quality Assessment Module (ablation) | QDMN baseline · DAVIS 2017 val | J&F: 82.9 -> 84.3 | Improved |
| add prior enhancement (ablation) | QDMN baseline · DAVIS 2017 val | J&F: 82.9 -> 83.6 | Improved |
| add both QAM and PE (ablation) | QDMN baseline · DAVIS 2017 val | J&F: 82.9 -> 84.6 | Improved |
| add QAM as plugin | STM · DAVIS 2017 val | J&F: 81.5 -> 83.6 | Improved |
| add QAM as plugin | KMN · DAVIS 2017 val | J&F: 82.6 -> 84.7 | Improved |
| add QAM as plugin | STCN · DAVIS 2017 val | J&F: 84.6 -> 85.6 | Improved |
| filter memory frames with QAM only at inference (sigma 0.8) (ablation) | STM · DAVIS 2017 val | J&F: 81.5 -> 82.5 | Improved |
| filter memory frames with QAM only at inference (sigma 0.8) (ablation) | MiVOS · DAVIS 2017 val | J&F: 82.7 -> 83.5 | Improved |
| use strong location prior instead of weak prior (ablation) | QDMN · YouTube-VOS | G: 83.0 -> 80.7 | Hurt |
| use strong location prior instead of weak prior (ablation) | QDMN · DAVIS 2017 val | J&F: 84.6 -> 85.2 | Mixed |
| train with synthetic BL30K data | QDMN · DAVIS 2017 test-dev | J&F: 77.7 -> 81.9 | Improved |
| set memory threshold to zero (no filtering) (ablation) | QDMN · DAVIS 2017 test-dev | J&F | Hurt |
Closest papers by meaning
- Learning High-Quality Dynamic Memory for Video Object Segmentation (TPAMI 2025 · similarity 0.99)
- Recurrent Dynamic Embedding for Video Object Segmentation (CVPR 2022 · similarity 0.89)
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.89)
- Learning Video Object Segmentation With Visual Memory (ICCV 2017 · similarity 0.89)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
- RMem: Restricted Memory Banks Improve Video Object Segmentation (CVPR 2024 · similarity 0.87)
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.
