Research map / Video / Video segmentation and tracking
Unsupervised Semantic Scene Labeling for Streaming Data
Maggie Wigness, John G. Rogers III
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 USSL instead of GBH | Video segmentation · Six-video average | AVG-ACC: 0.492 -> 0.527 | Improved |
| Use USSL instead of GBH | Video segmentation · Six-video average | OVERALL-ACC: 0.796 -> 0.781 | Hurt |
| Use USSL instead of S-GBH | Video segmentation · Six-video average | AVG-ACC: 0.452 -> 0.527 | Improved |
| Use USSL instead of S-GBH | Video segmentation · Six-video average | OVERALL-ACC: 0.710 -> 0.781 | Improved |
| Use USSL instead of GBH | Video segmentation · container | OVERALL-ACC: 0.786 -> 0.907 | Improved |
| Use USSL instead of GBH | Video segmentation · bus | OVERALL-ACC: 0.647 -> 0.401 | Hurt |
| Use USSL instead of GBH | Video segmentation · garden | OVERALL-ACC: 0.689 -> 0.686 | No clear effect |
| Use USSL instead of GBH | Video segmentation · ice | OVERALL-ACC: 0.898 -> 0.941 | Improved |
| Use USSL instead of GBH | Video segmentation · soccer | OVERALL-ACC: 0.876 -> 0.910 | Improved |
| Use USSL instead of GBH | Video segmentation · stefan | OVERALL-ACC: 0.878 -> 0.841 | Hurt |
| Use USSL instead of S-GBH | Video segmentation · bus | OVERALL-ACC: 0.370 -> 0.401 | Improved |
| Use USSL instead of S-GBH | Video segmentation · container | OVERALL-ACC: 0.855 -> 0.907 | Improved |
Closest papers by meaning
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.89)
- Semantic Video Segmentation by Gated Recurrent Flow Propagation (CVPR 2018 · similarity 0.89)
- Segment Anything without Supervision (NeurIPS 2024 · similarity 0.88)
- Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation (CVPR 2025 · similarity 0.88)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.88)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · 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.
