Research map / 3D vision / Human pose estimation
JA-POLS: A Moving-Camera Background Model via Joint Alignment and Partially-Overlapping Local Subspaces
Irit Chelly, Vlad Winter, Dor Litvak, David Rosen, Oren Freifeld
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 JA-POLS instead of PRPCA | moving-camera background modeling · Tennis | F-measure: 0.54 ± 0.03 -> 0.67 ± 0.03 | Improved |
| Use JA-POLS instead of PRPCA | moving-camera background modeling · Swing | F-measure: 0.59 ± 0.05 -> 0.62 ± 0.02 | Improved |
| Use JA-POLS instead of PRPCA | moving-camera background modeling · Stroller | F-measure: 0.50 ± 0.05 -> 0.62 ± 0.03 | Improved |
| Use JA-POLS instead of PRPCA | moving-camera background modeling · Flamingo | F-measure: 0.50 ± 0.01 -> 0.58 ± 0.01 | Improved |
| Use JA-POLS instead of PRPCA | moving-camera background modeling · Hike | F-measure: 0.70 ± 0.06 -> 0.74 ± 0.01 | Improved |
| Use JA-POLS instead of PRPCA | moving-camera background modeling · Horse | F-measure: 0.61 ± 0.05 -> 0.80 ± 0.01 | Improved |
| Use JA-POLS instead of PRPCA | moving-camera background modeling · Stunt | F-measure: 0.39 ± 0.11 -> 0.48 ± 0.10 | Improved |
| Use JA-POLS instead of Prac-ReProCS | moving-camera background modeling · ContinuousPan | F-measure: 0.59 ± 0.05 -> 0.67 ± 0.05 | Improved |
| Use JA-POLS instead of Prac-ReProCS | moving-camera background modeling · Jitter | F-measure: 0.75 ± 0.04 -> 0.83 ± 0.03 | Improved |
| Use JA-POLS instead of Prac-ReProCS | moving-camera background modeling · GardenShort | F-measure: 0.71 ± 0.01 -> 0.83 ± 0.01 | Improved |
| Use JA-POLS instead of incPCP-PTI | moving-camera background modeling · Kitchen | F-measure: 0.24 ± 0.04 -> 0.57 ± 0.07 | Improved |
| Use JA-POLS instead of Prac-ReProCS | moving-camera background modeling · FastMotion | F-measure: 0.27 ± 0.03 -> 0.41 ± 0.05 | Improved |
Closest papers by meaning
- A Deep Moving-Camera Background Model (ECCV 2022 · similarity 0.88)
- Spatio-Temporal Matching for Human Pose Estimation in Video (TPAMI 2016 · similarity 0.84)
- Spatiotemporal Bundle Adjustment for Dynamic 3D Human Reconstruction in the Wild (TPAMI 2020 · similarity 0.84)
- TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (NeurIPS 2024 · similarity 0.84)
- ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation (NeurIPS 2026 · similarity 0.83)
- Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better (CVPR 2025 · 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.
