Research map / Video / Video segmentation and tracking
One-Shot Video Object Segmentation
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 |
|---|---|---|---|
| Use OSVOS rather than OFL | DAVIS validation · DAVIS validation | J mean: 79.8 vs 68.0 | Helped |
| Use OSVOS rather than OFL | DAVIS validation · DAVIS validation | F mean: 80.6 vs 63.4 | Helped |
| Add boundary snapping (ablation) | OSVOS · DAVIS validation | J mean: 77.4 -> 79.8 | Helped |
| Add DAVIS parent-network pretraining (ablation) | OSVOS · DAVIS validation | J mean: 64.6 -> 79.8 | Helped |
| Add sequence-specific one-shot learning (ablation) | OSVOS · DAVIS validation | J mean: 52.5 -> 79.8 | Helped |
| Add both DAVIS pretraining and sequence-specific one-shot learning (ablation) | OSVOS · DAVIS validation | J mean: 17.6 -> 79.8 | Helped |
| Increase sequence-specific annotated frames from 1 to 2 | OSVOS · DAVIS sequences | J quality: 79.8 -> 84.6 | Helped |
| Increase sequence-specific annotated frames from 2 to 5 | OSVOS · DAVIS sequences | J quality: 84.6 -> 87.5 | Helped |
| Use 200 rather than 2079 parent-network training images | OSVOS -BS · DAVIS validation | J mean: 77.4 vs 76.9 | Hurt |
| Use OSVOS rather than OFL | Youtube-Objects · Youtube-Objects | mean IoU: 77.6 -> 78.3 | Helped |
Closest papers by meaning
- Make One-Shot Video Object Segmentation Efficient Again (NeurIPS 2020 · similarity 0.92)
- Segment Anything Across Shots: A Method and Benchmark (AAAI 2026 · similarity 0.89)
- BubbleNets: Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames (CVPR 2019 · similarity 0.88)
- What Ails One-Shot Image Segmentation: A Data Perspective (NeurIPS 2021 · similarity 0.88)
- Beyond Pixel and Object: Part Feature as Reference for Few-Shot Video Object Segmentation (AAAI 2025 · similarity 0.87)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 2025 · 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.