Research map / Video / Video segmentation and tracking
Video Object Segmentation With Dynamic Memory Networks and Adaptive Object Alignment
Shuxian Liang, Xu Shen, Jianqiang Huang, Xian-Sheng Hua
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 DMN (dynamic memory template) to fixed first-frame template (ablation) | Base model · DAVIS 2017 val | G: 77.8 -> 80.5 | Improved |
| add AOA (adaptive object alignment) to base model (ablation) | Base model · DAVIS 2017 val | G: 77.8 -> 78.9 | Improved |
| use object features instead of frame features in memory encoder (ablation) | Full model · DAVIS 2017 val | G: 79.4 -> 81.3 | Improved |
| add matcher with AOA and proposals (vs decoding masks from DMN) (ablation) | Full model · DAVIS 2017 val | G: 70.0 -> 81.3 | Improved |
| add RefineNet on coarse masks (ablation) | Full model · DAVIS 2017 val | G: 69.2 -> 81.3 | Improved |
| add intermediate memory frames (stride 5) to first+previous (ablation) | Full model · DAVIS 2017 val | G: 80.4 -> 81.3 | Improved |
| use all past frames in memory instead of stride-5 sampling (ablation) | Full model · DAVIS 2017 val | G / time: 81.3 -> 81.8 (0.15 -> 0.19 s/frame) | Mixed |
| add main training on videos after pre-training (ablation) | Full model · DAVIS 2017 val | G: 72.5 -> 81.3 | Improved |
| add pre-training on COCO images before main training (ablation) | Full model · DAVIS 2017 val | G: 67.9 -> 81.3 | Improved |
| tune proposal generator on small DAVIS instead of COCO-pretrained only (ablation) | Full model · DAVIS 2017 val | G: 80.1 -> 79.0 | Hurt |
| tune proposal generator on YTVOS (ablation) | Full model · DAVIS 2017 val | G: 80.1 -> 81.3 | Improved |
| use DMN with first frame only vs AOA-only base (ablation) | Base w/ AOA · DAVIS 2017 val | G: 78.9 -> 79.9 | Improved |
Closest papers by meaning
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.92)
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.91)
- Learning Position and Target Consistency for Memory-Based Video Object Segmentation (CVPR 2021 · similarity 0.91)
- Hierarchical Memory Matching Network for Video Object Segmentation (ICCV 2021 · similarity 0.90)
- Learning When and How to Update Memory for Video Object Segmentation (TPAMI 2026 · similarity 0.90)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.89)
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.
