Research map / Video / Video segmentation and tracking
Coherent Parametric Contours for Interactive 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 coherent parametric contours with spatio-temporal optimization instead of scribble-based segmentation | video object segmentation · CPC dataset, len=6, th=1 | spatial accuracy: 0.618 -> 0.834 | Helped |
| Use coherent parametric contours with spatio-temporal optimization instead of global plane tracking | video object segmentation · CPC dataset, len=11, th=1 | spatial accuracy: 0.608 -> 0.757 | Helped |
| Use coherent parametric contours with spatio-temporal optimization instead of scribble-based segmentation | video object segmentation · CPC dataset, len=11, th=1 | temporal consistency: 0.643 -> 0.818 | Helped |
| Use coherent parametric contours with spatio-temporal optimization instead of global plane tracking | video object segmentation · CPC dataset, len=6, th=1 | temporal consistency: 0.768 -> 0.866 | Helped |
| Add spatio-temporal optimization to locally rigid motion warping (ablation) | CPC · CPC dataset, len=6, th=1 | spatial accuracy: 0.688 -> 0.834 | Helped |
| Add spatio-temporal optimization to locally rigid motion warping (ablation) | CPC · CPC dataset, len=11, th=1 | temporal consistency: 0.703 -> 0.818 | Helped |
| Replace global plane motion with locally rigid motion | video object segmentation · non-rigid-motion sequences | spatial accuracy | Helped |
| Use local boundary editing with parametric curves rather than scribble refinement | interactive video object segmentation · Minion and Tower user-study clips | editing time | Helped |
Closest papers by meaning
- Video Segmentation via Object Flow (CVPR 2016 · similarity 0.87)
- Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps (CVPR 2021 · similarity 0.87)
- SharpContour: A Contour-Based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation (CVPR 2022 · similarity 0.86)
- Using Diffusion Priors for Video Amodal Segmentation (CVPR 2025 · similarity 0.85)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (CVPR 2025 · similarity 0.84)
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024 · similarity 0.83)
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.