Research map / Video / Video segmentation and tracking
CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF
Read the paperCheck 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 |
|---|---|---|---|
| Combine temporal fusion with CNN mask refinement (ablation) | OSVOS + linear motion baseline · DAVIS 2017 validation | Global Mean: 0.596 -> 0.706 | Helped |
| Enable temporal fusion only (ablation) | OSVOS + linear motion baseline · DAVIS 2017 validation | Global Mean: 0.596 -> 0.589 | Hurt |
| Enable CNN mask refinement only (ablation) | OSVOS + linear motion baseline · DAVIS 2017 validation | Global Mean: 0.596 -> 0.648 | Helped |
| Increase combined temporal-fusion and mask-refinement iterations from 3 to 5 (ablation) | CNN-in-MRF · DAVIS 2017 validation | Global Mean: 0.706 -> 0.707 | No clear effect |
| Use CNN-based spatio-temporal MRF inference initialized with OSVOS | OSVOS · DAVIS 2017 test-dev | Global Mean: 0.505 -> 0.675 | Helped |
| Use CNN-based spatio-temporal MRF inference initialized with OSVOS | OSVOS · DAVIS 2016 | Region IoU J: 0.857 -> 0.842 | Hurt |
| Use CNN-based spatio-temporal MRF inference initialized with OSVOS | OSVOS · YouTube-Objects | Region IoU J: 0.783 -> 0.784 | Helped |
| Use CNN-based spatio-temporal MRF inference initialized with OSVOS | OSVOS · SegTrack v2 | Region IoU J: 0.781 -> 0.771 | Hurt |
Closest papers by meaning
- Spatiotemporal CNN for Video Object Segmentation (CVPR 2019 · similarity 0.88)
- From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models (NeurIPS 2023 · similarity 0.87)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 2025 · similarity 0.87)
- Budget-Aware Deep Semantic Video Segmentation (CVPR 2017 · similarity 0.87)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.86)
- MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation (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.