Research map / Video / Video segmentation and tracking
FEELVOS: Fast End-To-End Embedding Learning for 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 FEELVOS without first-frame fine-tuning instead of RGMP | Video object segmentation · DAVIS 2017 validation | J&F: 66.7 -> 71.5 | Helped |
| Train FEELVOS with YouTube-VOS data | FEELVOS · DAVIS 2017 validation | J&F: 69.1 -> 71.5 | Helped |
| Train FEELVOS with YouTube-VOS data | FEELVOS · DAVIS 2017 test-dev | J&F: 54.4 -> 57.8 | Helped |
| Replace previous-frame local matching with previous-frame global matching (ablation) | FEELVOS · DAVIS 2017 validation | J&F: 69.1 -> 64.2 | Hurt |
| Remove previous-frame matching (ablation) | FEELVOS · DAVIS 2017 validation | J&F: 69.1 -> 54.9 | Hurt |
| Remove previous-frame matching and previous-frame prediction features (ablation) | FEELVOS · DAVIS 2017 validation | J&F: 69.1 -> 52.6 | Hurt |
| Remove previous-frame prediction features while retaining local matching (ablation) | FEELVOS · DAVIS 2017 validation | J&F: 69.1 -> 63.3 | Hurt |
| Remove first-frame global matching (ablation) | FEELVOS · DAVIS 2017 validation | J&F: 69.1 -> 56.1 | Hurt |
Closest papers by meaning
- Make One-Shot Video Object Segmentation Efficient Again (NeurIPS 2020 · similarity 0.89)
- Siamese Network with Interactive Transformer for Video Object Segmentation (AAAI 2022 · similarity 0.88)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.88)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
- VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models (CVPR 2025 · similarity 0.86)
- 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.