Research map / Video / Video segmentation and tracking
Spatial-Temporal Gaussian Scale Mixture Modeling for Foreground Estimation
Qian Ning, Weisheng Dong, Fangfang Wu, Jinjian Wu, Jie Lin, Guangming Shi
Read the paperCheck 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 |
|---|---|---|---|
| add temporal nonzero-mean prior from previous frame (GSM -> TGSM) (ablation) | GSM foreground model · CD 2012 | average F-measure (%): 82.50 -> 86.12 | Improved |
| add local spatial grouping of pixels (TGSM -> STGSM) (ablation) | TGSM · CD 2012 | average F-measure (%): 86.12 -> 89.25 | Improved |
| temporal prior on Intermittent Object Motion category (ablation) | GSM · CD 2012 Intermittent Obj. Mot. | F-measure (%): 69.00 -> 86.47 | Improved |
| temporal prior on Baseline category (ablation) | GSM · CD 2012 Baseline | F-measure (%): 93.00 -> 93.4 | Improved |
| STGSM with 5x5 block grouping vs SGSM-BS with superpixel grouping | STGSM · PTIS | average F-measure (%): 83.41 -> 83.17 | No clear effect |
| STGSM temporal+block model vs SGSM-BS-block | block-grouped GSM · PTIS | average F-measure (%): 77.70 -> 83.17 | Improved |
| STGSM vs SGSM-BS | SGSM-BS · CD 2012 | average F-measure (%): 86.00 -> 89.25 | Improved |
| add optical flow and temporal modeling (STGSM) vs SGSM-BS | SGSM-BS · Running time | time (s): 27.39 -> 41.49 | Hurt |
Closest papers by meaning
- Foreground Segmentation with Tree-Structured Sparse RPCA (TPAMI 2017 · similarity 0.88)
- Robust Online Matrix Factorization for Dynamic Background Subtraction (TPAMI 2017 · similarity 0.88)
- Spatiotemporal GMM for Background Subtraction with Superpixel Hierarchy (TPAMI 2017 · similarity 0.87)
- SfM-Free 3D Gaussian Splatting via Hierarchical Training (CVPR 2025 · similarity 0.83)
- GG-SSMs: Graph-Generating State Space Models (CVPR 2025 · similarity 0.83)
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos (NeurIPS 2025 · similarity 0.82)
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.
