Research map / Detection and segmentation / CNN features
Fast Boosting Based Detection Using Scale Invariant Multimodal Multiresolution Filtered Features
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 |
|---|---|---|---|
| add theoretical scale correction to color features (ablation) | MM-MRFC · Caltech-USA reasonable test, standard training set | miss rate: 24.46 -> 22.84 | Helped |
| add empirical scale correction to color features (ablation) | MM-MRFC · Caltech-USA reasonable test, standard training set | miss rate: 24.46 -> 22.69 | Helped |
| add 2D spatial context (ablation) | MM-MRFC · Caltech-USA reasonable test, standard training set | miss rate: 22.84 -> 20.80 | Helped |
| add 2D symmetry context (ablation) | MM-MRFC · Caltech-USA reasonable test, standard training set | miss rate: 20.80 -> 18.26 | Helped |
| add SDt motion channels (ablation) | MM-MRFC · Caltech-USA reasonable test, standard training set | miss rate: 18.26 -> 17.29 | Helped |
| apply multiresolution filtering to SDt motion channels (ablation) | MM-MRFC · Caltech-USA reasonable test, standard training set | miss rate: 17.29 -> 16.11 | Helped |
| add scale correction (ablation) | MRFC · KITTI validation, color | AP: 62.84 -> 67.14; 59.98 -> 61.45; 51.10 -> 52.76 | Helped |
| add 2D spatial context (ablation) | MM-MRFC · KITTI validation, color | AP: 67.14 -> 69.58; 61.45 -> 63.83; 52.76 -> 54.83 | Helped |
| add 2D symmetry context (ablation) | MM-MRFC · KITTI validation, color | AP: 69.58 -> 70.28; 63.83 -> 64.75; 54.83 -> 55.66 | Helped |
| add 3D geometric context after 3D spatial context (ablation) | MM-MRFC with stereo depth · KITTI validation | AP: 77.88 -> 77.97; 70.30 -> 70.61; 60.63 -> 61.47 | Mixed |
| add multiresolution filtered channels after stereo 3D context (ablation) | MM-MRFC with stereo depth · KITTI validation | AP: 77.97 -> 82.53; 70.61 -> 74.82; 61.47 -> 65.95 | Helped |
| add 3D geometric context after 3D spatial context (ablation) | MM-MRFC with LIDAR depth · KITTI validation | AP: 77.88 -> 79.92; 70.93 -> 72.48; 61.91 -> 63.13 | Helped |
Closest papers by meaning
- Semantic Channels for Fast Pedestrian Detection (CVPR 2016 · similarity 0.84)
- DyFCLT: Dynamic Frequency-Decoupled Cross-Modal Learning Transformer for Multimodal Tiny Object Detection (CVPR 2026 · similarity 0.83)
- Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 2025 · similarity 0.82)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.82)
- SSLFusion: Scale and Space Aligned Latent Fusion Model for Multimodal 3D Object Detection (AAAI 2025 · similarity 0.82)
- Unsupervised Object Detection with Theoretical Guarantees (NeurIPS 2024 · 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.