Research map / Video / Video segmentation and tracking
Hierarchical Memory Matching Network for Video Object Segmentation
Hongje Seong, Seoung Wug Oh, Joon-Young Lee, Seongwon Lee, Suhyeon Lee, 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 kernel guided memory matching (ablation) | STM · DAVIS 2017 val | J&F: 82.2 -> 83.1 | Improved |
| use kernel guided matching instead of KMN kernelization (ablation) | STM · DAVIS 2017 val / YouTube-VOS 2019 | J&F / G: 83.3 -> 83.1 (DAVIS), 80.0 -> 80.9 (YT19) | Mixed |
| add top-k guided fine-scale memory matching (ablation) | STM · DAVIS 2017 val | J&F: 82.2 -> 83.6 | Improved |
| add top-k guided matching on top of kernel guidance (ablation) | HMMN · DAVIS 2017 val | J&F: 83.1 -> 84.7 | Improved |
| select fine-scale pixels with top-k instead of random (ablation) | HMMN · DAVIS 2017 val | J&F: 81.9 -> 84.7 | Improved |
| add dropout in top-k memory module (ablation) | HMMN · DAVIS 2017 val | J&F: 81.5 -> 84.7 | Improved |
| use dense fine-scale memory instead of top-k (ablation) | HMMN · DAVIS 2017 val | J&F: 84.7 -> 82.0 | Hurt |
| add res2 and res3 fine-scale memory (ablation) | HMMN · DAVIS 2017 val | J&F: 83.1 -> 84.7 | Improved |
| use intermediate frames for fine-scale memory (ablation) | HMMN · DAVIS 2017 val | J&F: 84.7 -> 84.9 | No clear effect |
| use local 7x7 window instead of global matching in kernel tracking (ablation) | HMMN · DAVIS 2017 val | J&F: 84.2 -> 84.7 | Improved |
| set sigma_init to 3 instead of 1 (ablation) | HMMN · DAVIS 2017 val | J&F: 83.6 -> 84.7 | Improved |
| increase inference k from 32 to 64 (ablation) | HMMN · DAVIS 2017 val | J&F: 84.7 -> 84.9 | No clear effect |
Closest papers by meaning
- Efficient Regional Memory Network for Video Object Segmentation (CVPR 2021 · similarity 0.91)
- Video Object Segmentation With Dynamic Memory Networks and Adaptive Object Alignment (ICCV 2021 · similarity 0.90)
- Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels (TPAMI 2022 · similarity 0.90)
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.89)
- Kernelized Memory Network for Video Object Segmentation (ECCV 2020 · similarity 0.89)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · 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.
