Research map / Video / Video segmentation and tracking
CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
Kevin Duarte, Yogesh S. Rawat, Mubarak Shah
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 the learned zooming module (ablation) | CapsuleVOS · Youtube-VOS val | Overall: 54.3 -> 62.3 | Improved |
| add learned zooming instead of hand-crafted bounding box (ablation) | CapsuleVOS · Youtube-VOS val | Overall: 60.4 -> 62.3 | Improved |
| use hand-crafted zooming instead of no zooming (ablation) | CapsuleVOS · Youtube-VOS val | Overall: 54.3 -> 60.4 | Improved |
| use attention-based routing instead of concatenation EM routing (ablation) | CapsuleVOS · Youtube-VOS val | Overall: 59.7 -> 62.3 | Improved |
| use capsules with attention routing instead of fully convolutional network (ablation) | CapsuleVOS · Youtube-VOS val | Overall: 59.4 -> 62.3 | Improved |
| concatenation EM routing versus fully convolutional network (ablation) | CapsuleVOS · Youtube-VOS val | Overall: 59.7 vs 59.4 | No clear effect |
| add the ConvLSTM memory module (ablation) | CapsuleVOS · Youtube-VOS val | Overall: 58.4 -> 62.3 | Improved |
| use capsule model without online learning versus DyeNet | CapsuleVOS · DAVIS-2017 test-dev | Global mean: 62.5 vs 51.3 | Hurt |
| CapsuleVOS without online learning versus OSVOS with online learning | CapsuleVOS · Youtube-VOS val | Overall: 58.8 -> 62.3 | Improved |
Closest papers by meaning
- Video Object Segmentation Using Space-Time Memory Networks (ICCV 2019 · similarity 0.90)
- Video Object Segmentation without Temporal Information (TPAMI 2018 · similarity 0.89)
- Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels (TPAMI 2022 · similarity 0.89)
- Video Object Segmentation With Dynamic Memory Networks and Adaptive Object Alignment (ICCV 2021 · similarity 0.89)
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.89)
- Exploring the Semi-Supervised Video Object Segmentation Problem from a Cyclic Perspective (IJCV 2022 · 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.
