Research map / Video / Video segmentation and tracking
BubbleNets: Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Select the annotation frame with BN0 rather than the first frame | OSVOS · DAVIS 2017 Val. | J+F: 113.3 -> 125.2 | Helped |
| Select the annotation frame with BN0 rather than the first frame | OSVOS · DAVIS 2016 Val. | J+F: 152.8 -> 159.8 | Helped |
| Select the annotation frame with BN LF rather than the first frame | OSVOS · SegTrackv2 | J+F: 122.3 -> 134.7 | Helped |
| Select the annotation frame with BN LF rather than the first frame | OSVOS · YT-VOS (1st 1,000) | J+F: 107.3 -> 115.5 | Helped |
| Select the annotation frame with BN0 rather than the first frame | OnAVOS · DAVIS 2017 Val. | J+F: 63.9 -> 69.2 | Helped |
| Remove normalized frame indices (ablation) | BubbleNets BN0 · DAVIS 2017 Val. | J+F: 125.2 -> 123.8 | Hurt |
| Remove reference frames (ablation) | BubbleNets BN0 · DAVIS 2017 Val. | J: 59.7 -> 55.4 | Hurt |
| Predict single-frame performance instead of relative frame performance (ablation) | BubbleNets BN0 · DAVIS 2017 Val. | J: 59.7 -> 55.1 | Hurt |
| Use a middle-frame-biased loss (ablation) | BubbleNets BN0 · DAVIS 2017 Val. | J: 59.7 -> 57.8 | Hurt |
| Increase comparison batch size from 1 to 5 (ablation) | BubbleNets BN0 · DAVIS 2017 Val. | J+F: 124.1 -> 125.2 | Helped |
| Increase comparison batch size from 5 to 20 (ablation) | BubbleNets BN0 · DAVIS 2017 Val. | J+F: 125.2 -> 123.6 | Hurt |
| Increase comparison batch size from 1 to 5 (ablation) | BubbleNets BN NIFI · DAVIS 2017 Val. | J+F: 122.9 -> 123.8 | Helped |
Closest papers by meaning
- One-Shot Video Object Segmentation (CVPR 2017 · similarity 0.88)
- Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks (CVPR 2019 · similarity 0.88)
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.88)
- Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation (CVPR 2022 · similarity 0.88)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · 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.