Research map / Video / Video segmentation and tracking
Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions
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 |
|---|---|---|---|
| add temporal consistency term Lc to the loss (ablation) | 3D U-net motion segmentation network · DAVIS2016 val | J: 33.1 to 73.2 | Helped |
| use spatio-temporal parametric motion model instead of spatial quadratic per frame (ablation) | 3D U-net motion segmentation network · DAVIS2016 val | J: 70.5 to 73.2 | Helped |
| unsupervised space-time flow segmentation vs. other unsupervised flow-only methods | proposed method · DAVIS2016 val | J: 73.2 vs EM 69.3, MoSeg 68.3, OCLR 72.1 | Mixed |
| use of optical flow sub-volume with temporal linkage on SegTrackV2 | proposed method · SegTrackV2 | J: 55.0 vs EM 55.5 | No clear effect |
Closest papers by meaning
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.91)
- FlowFeat: Pixel-Dense Embedding of Motion Profiles (NeurIPS 2025 · similarity 0.87)
- UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model (CVPR 2024 · similarity 0.87)
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time (NeurIPS 2026 · similarity 0.86)
- Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation (CVPR 2024 · similarity 0.86)
- Know Where You Are From: Event-Based Segmentation via Spatio-Temporal Propagation (AAAI 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.