Research map / Video / Video segmentation and tracking
Kernelized Memory Network for Video Object Segmentation
Hongje Seong, Junhyuk Hyun, Euntai Kim
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 Hide-and-Seek pre-training (ablation) | KMN · DAVIS 2016 val | G_M: 81.3 -> 87.1 | Improved |
| add Hide-and-Seek pre-training (ablation) | KMN · DAVIS 2017 val | G_M: 72.6 -> 75.9 | Improved |
| add Hide-and-Seek pre-training (ablation) | KMN · Youtube-VOS 2018 val | Overall: 79.0 -> 79.5 | Improved |
| add kernelized memory read (ablation) | KMN · DAVIS 2016 val | G_M: 81.3 -> 87.2 | Improved |
| add kernelized memory read (ablation) | KMN · DAVIS 2017 val | G_M: 72.6 -> 73.5 | Improved |
| add kernelized memory read (ablation) | KMN · Youtube-VOS 2018 val | Overall: 79.0 -> 81.0 | Improved |
| add kernelized memory read to Hide-and-Seek model (ablation) | KMN · DAVIS 2016 val | G_M: 87.1 -> 87.6 | Improved |
| add kernelized memory read to Hide-and-Seek model (ablation) | KMN · DAVIS 2017 val | G_M: 75.9 -> 76.0 | Improved |
| add kernelized memory read to Hide-and-Seek model (ablation) | KMN · Youtube-VOS 2018 val | Overall: 79.5 -> 81.4 | Improved |
| add Hide-and-Seek to kernelized-read model (ablation) | KMN · Youtube-VOS 2018 val | Overall: 81.0 -> 81.4 | Improved |
| add Hide-and-Seek to kernelized-read model (ablation) | KMN · DAVIS 2017 val | G_M: 73.5 -> 76.0 | Improved |
| add Youtube-VOS to DAVIS training data | KMN · DAVIS 2017 val | G_M: 76.0 -> 82.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RaNet — RANet: Ranking Attention Network for Fast Video Object Segmentation (ICCV 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels (TPAMI 2022 · similarity 0.99)
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.91)
- Efficient Regional Memory Network for Video Object Segmentation (CVPR 2021 · similarity 0.91)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.90)
- RMem: Restricted Memory Banks Improve Video Object Segmentation (CVPR 2024 · similarity 0.88)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.88)
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.
