Research map / Video / Video segmentation and tracking
Interactive Video Object Segmentation Using Global and Local Transfer Modules
Yuk Heo, Yeong Jun Koh, Chang-Su 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 local transfer module (ablation) | Proposed interactive VOS · DAVIS2017 val, round 1 | J: 0.629 -> 0.676 | Improved |
| add local transfer module (ablation) | Proposed interactive VOS · DAVIS2017 val, round 5 | J: 0.771 -> 0.783 | Improved |
| use front TE instead of rear TE features for local affinity (ablation) | Proposed interactive VOS · DAVIS2017 val, round 1 | J: 0.653 -> 0.676 | Improved |
| use front TE instead of rear TE features (ablation) | Proposed interactive VOS · DAVIS2017 val, round 5 | J: 0.760 -> 0.783 | Improved |
| add auxiliary loss (lambda 0 -> 0.1) (ablation) | Proposed interactive VOS · DAVIS2017 val, round 1 | J: 0.645 -> 0.676 | Improved |
| add auxiliary loss (lambda 0 -> 0.1) (ablation) | Proposed interactive VOS · DAVIS2017 val, round 5 | J: 0.761 -> 0.783 | Improved |
| lambda 0.5 instead of 0.1 (ablation) | Proposed interactive VOS · DAVIS2017 val, round 1 | J: 0.676 -> 0.658 | Hurt |
| lambda 1.0 instead of 0.1 (ablation) | Proposed interactive VOS · DAVIS2017 val, round 5 | J: 0.783 -> 0.762 | Hurt |
| use probability transfer modules instead of matching (A-Net predictions) (ablation) | Proposed interactive VOS · DAVIS2017 val | AUC-J: 0.636 -> 0.771 | Improved |
| use probability transfer modules instead of matching (scribbles) (ablation) | Proposed interactive VOS · DAVIS2017 val | J&F@60s: 0.690 -> 0.827 | Improved |
| compare with Oh et al. in user study | Proposed interactive VOS · DAVIS2016 user study | seconds per video: 37.9 -> 29.8 | Improved |
| compare with Oh et al. in user study | Proposed interactive VOS · DAVIS2016 user study | rounds per video: 2.77 -> 1.90 | Improved |
Closest papers by meaning
- Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks (CVPR 2019 · similarity 0.91)
- Efficient Video Object Segmentation via Network Modulation (CVPR 2018 · similarity 0.88)
- BubbleNets: Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames (CVPR 2019 · similarity 0.88)
- A Survey on Deep Learning Technique for Video Segmentation (TPAMI 2022 · similarity 0.88)
- Space-Time Memory Networks for Video Object Segmentation With User Guidance (TPAMI 2020 · similarity 0.87)
- Online Video Object Segmentation via Convolutional Trident Network (CVPR 2017 · similarity 0.87)
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.
