Research map / Video / Video segmentation and tracking
Video Segmentation via Object Flow
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 |
|---|---|---|---|
| Jointly optimize segmentation and object-conditioned optical flow | Object Flow · SegTrack v2 | mean per-object overlap ratio: 71.8 -> 74.1 | Helped |
| Jointly optimize segmentation and object-conditioned optical flow | Object Flow · Youtube-Objects | mean overlap ratio: 74.0 -> 77.6 | Helped |
| Use the multi-level pixel-superpixel model rather than pixels alone (ablation) | Object Flow · SegTrack v2 | mean per-object overlap ratio: 69.6 -> 74.1 | Helped |
| Use the multi-level pixel-superpixel model rather than superpixels alone (ablation) | Object Flow · SegTrack v2 | mean per-object overlap ratio: 50.3 -> 65.6 | Helped |
| Re-estimate optical flow using segmented foreground and background regions | Object Flow · SegTrack v2 sequences relying on optical flow | segmentation overlap ratio: 72.9% to 75.1% | Helped |
| Use segmentation-conditioned updated optical flow instead of initial flow | Object Flow · SegTrack v2 significant-motion frames | warped-mask overlap ratio: 71.6 -> 74.5 | Helped |
| Use segmentation-conditioned updated optical flow | Object Flow · SegTrack v2 significant-motion frames | normalized interpolation error: 0.32 -> 0.36 | Hurt |
Closest papers by meaning
- Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow (AAAI 2020 · similarity 0.91)
- Optical Flow With Semantic Segmentation and Localized Layers (CVPR 2016 · similarity 0.91)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.89)
- Segment Any Motion in Videos (CVPR 2025 · similarity 0.89)
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time (NeurIPS 2026 · similarity 0.87)
- FlowFeat: Pixel-Dense Embedding of Motion Profiles (NeurIPS 2025 · 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.