Research map / Video / Video segmentation and tracking
DetectSCI: Toward Object-Guided ROI Reconstruction for High-Resolution Video Snapshot Compressive Imaging
Xingjian Jiang, Lishun Wang, Ping Wang, Xin Yuan
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 INR block to RT-DETR baseline (ablation) | RT-DETR · SportsMOT SCI | AP: 76.8 -> 79.5 | Improved |
| add multi-scale spatial Mamba block to RT-DETR baseline (ablation) | RT-DETR · SportsMOT SCI | AP: 76.8 -> 79.6 | Improved |
| combine single-scale MSM with INR (ablation) | MSM only · SportsMOT SCI | AP: 79.6 -> 79.9 | Improved |
| use independent multi-scale MSM (ablation) | single-scale MIM · SportsMOT SCI | AP: 79.9 -> 82.5 | Improved |
| share weights across scales in MIM (ablation) | independent MIM · SportsMOT SCI | AP: 82.5 -> 80.9; params 61.2M -> 53.1M | Mixed |
| add Frequency Mamba (all bands fused) (ablation) | DetectSCI without FM · SportsMOT SCI | AP: 78.4 -> 80.9 | Improved |
| add low-frequency branch only (ablation) | DetectSCI without FM · SportsMOT SCI | AP: 78.4 -> 78.8 | Improved |
| add high-frequency branch only (ablation) | DetectSCI without FM · SportsMOT SCI | AP: 78.4 -> 80.1 | Improved |
| fuse all three bands vs best single band (ablation) | high-frequency only FM · SportsMOT SCI | AP: 80.1 -> 80.9 | Improved |
Closest papers by meaning
- MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing (CVPR 2021 · similarity 0.90)
- EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging (CVPR 2023 · similarity 0.90)
- A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging (ECCV 2024 · similarity 0.89)
- Memory-Efficient Network for Large-Scale Video Compressive Sensing (CVPR 2021 · similarity 0.88)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.86)
- MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging (NeurIPS 2024 · similarity 0.85)
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.
