Research map / Video / Video segmentation and tracking
Global Spectral Filter Memory Network for Video Object Segmentation
Yong Liu, Ran Yu, Jiahao Wang, Xinyuan Zhao, Yitong Wang, Yansong Tang, Yujiu Yang
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 low-frequency module (LFM) to encoder (ablation) | STCN · DAVIS2017 val | J&F: 84.1 -> 84.7 | Improved |
| add high-frequency module (HFM) to decoder (ablation) | STCN · DAVIS2017 val | J&F: 84.1 -> 84.5 | Improved |
| add boundary branch to LFM (ablation) | STCN + LFM · DAVIS2017 val | J&F: 84.7 -> 85.0 | Improved |
| add LFM, HFM and boundary branch together (ablation) | STCN · DAVIS2017 val | J&F: 84.1 -> 85.3 | Improved |
| enhance high frequency in encoder instead of low frequency (ablation) | GSFM · DAVIS2017 val | J&F: 85.3 -> 84.2 | Hurt |
| enhance low frequency in decoder instead of high frequency (ablation) | GSFM · DAVIS2017 val | J&F: 85.3 -> 84.5 | Hurt |
| replace LFM with attention-based global fusion (ablation) | GSFM · DAVIS2017 val | J&F: 85.3 -> 84.9 | Hurt |
| enhance full frequency in encoder instead of low (ablation) | GSFM · DAVIS2017 val | J&F: 85.3 -> 84.8 | Hurt |
| add LFM/HFM to STM | STM · DAVIS2017 val | J&F: 81.5 -> 83.5 | Improved |
| add LFM/HFM to KMN | KMN · DAVIS2017 val | J&F: 82.6 -> 84.7 | Improved |
| add LFM/HFM to MiVOS | MiVOS · DAVIS2017 val | J&F: 82.7 -> 84.6 | Improved |
| GSFM versus STCN baseline | STCN · DAVIS2017 test-dev | J&F: 76.1 -> 77.5 | Improved |
Closest papers by meaning
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.89)
- Space-Time Memory Networks for Video Object Segmentation With User Guidance (TPAMI 2020 · similarity 0.89)
- Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels (TPAMI 2022 · similarity 0.89)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
- Generalizable Fourier Augmentation for Unsupervised Video Object Segmentation (AAAI 2024 · similarity 0.87)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 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.
