Research map / Detection and segmentation / Tracking
GridShift: A Faster Mode-Seeking Algorithm for Image Segmentation and Object Tracking
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 GridShift instead of MS++ | unsupervised clustering · Phone Gyroscope | ARI: 0.2354 -> 0.2401 | Helped |
| use GridShift instead of MS++ | unsupervised clustering · Phone Gyroscope | AMI: 0.1835 -> 0.1837 | No clear effect |
| use GridShift instead of MS++ | unsupervised clustering · Phone Gyroscope | runtime: 5324.19s -> 110.43s | Helped |
| use GridShift instead of MS++ | unsupervised clustering · Iris | ARI: 0.5681 -> 0.6246 | Helped |
| use GridShift instead of MS++ | unsupervised clustering · Iris | AMI: 0.7316 -> 0.8014 | Helped |
| use GridShift instead of SLIC | image segmentation · BSDS500 | average runtime: 0.078 -> 0.031 seconds | Helped |
| use GridShift instead of MS++ | image segmentation · BSDS500 | average runtime: 2.561 -> 0.031 seconds | Helped |
| add spatial coordinates x,y to RGB features (ablation) | GridShift image segmentation · BSDS500 | ARI: 488 | No clear effect |
| add spatial coordinates x,y to RGB features (ablation) | GridShift image segmentation · BSDS500 | FW: 492 | No clear effect |
| use USOT-GS instead of USOT | OTB100 tracking · OTB100 | AUC: 0.589 -> 0.651 | Helped |
| use GS instead of MS++ | unsupervised iterative tracking · OTB100 | AUC: 0.326 -> 0.638 | Helped |
Closest papers by meaning
- MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking (CVPR 2021 · similarity 0.95)
- AttentionShift: Iteratively Estimated Part-Based Attention Map for Pointly Supervised Instance Segmentation (CVPR 2023 · similarity 0.83)
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time (NeurIPS 2026 · similarity 0.82)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 2025 · similarity 0.81)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.81)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.81)
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.