Research map / Video / Video segmentation and tracking
Learning High-Quality Dynamic Memory for Video Object Segmentation
Yong Liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, Jiahao Wang, Yitong Wang, Yansong Tang, 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 QAM as a plugin (ablation) | STM · DAVIS 2017 val | J&F: 81.5 -> 83.6 | Improved |
| add QAM as a plugin (ablation) | KMN · DAVIS 2017 val | J&F: 82.6 -> 84.7 | Improved |
| add QAM as a plugin (ablation) | STCN · DAVIS 2017 val | J&F: 84.6 -> 85.6 | Improved |
| add QAM filtering at inference only (sigma 0 -> 0.8) (ablation) | STM · DAVIS 2017 val | J&F: 81.5 -> 82.5 | Improved |
| add QAM filtering at inference only (sigma 0 -> 0.8) (ablation) | KMN · DAVIS 2017 val | J&F: 82.6 -> 83.4 | Improved |
| add QAM filtering at inference only (sigma 0 -> 0.8) (ablation) | MiVOS · DAVIS 2017 val | J&F: 82.7 -> 83.5 | Improved |
| add QAM (ablation) | QDMN without PE · DAVIS 2017 val | J&F: 83.6 -> 84.6 | Improved |
| add prior enhancement (PE) (ablation) | QDMN without QAM · DAVIS 2017 val | J&F: 84.3 -> 84.6 | Improved |
| add QAM and PE to baseline (ablation) | STM-style baseline · DAVIS 2017 val | J&F: 82.9 -> 84.6 | Improved |
| use strong prior instead of weak prior (ablation) | QDMN · DAVIS 2017 val | J&F: 84.6 -> 85.2 | Improved |
| use strong prior instead of weak prior (ablation) | QDMN · YouTube-VOS | G: 83.0 -> 80.7 | Hurt |
| use memory interval 5 instead of 3 (ablation) | QDMN · DAVIS 2017 val | J&F: 85.2 -> 85.7 | Improved |
Closest papers by meaning
- Learning Quality-Aware Dynamic Memory for Video Object Segmentation (ECCV 2022 · similarity 0.99)
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.89)
- Recurrent Dynamic Embedding for Video Object Segmentation (CVPR 2022 · similarity 0.89)
- Efficient Regional Memory Network for Video Object Segmentation (CVPR 2021 · similarity 0.89)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.88)
- 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.
