Research map / 3D vision / Depth and stereo
Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs
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 |
|---|---|---|---|
| use multi-view ground-plane fusion with MVMS instead of the strongest listed baseline | wide-area crowd counting · PETS2009 test | MAE: 7.51 -> 3.49 | Helped |
| use multi-view ground-plane fusion with MVMS instead of the strongest listed baseline | wide-area crowd counting · DukeMTMC test | MAE: 2.12 -> 1.03 | Helped |
| use multi-view ground-plane fusion with MVMS instead of the strongest listed baseline | wide-area crowd counting · City Street test | MAE: 11.10 -> 8.01 | Helped |
| add projection normalization to late fusion (ablation) | Late fusion · PETS2009 test | MAE: 4.22 -> 3.92 | Helped |
| add projection normalization to late fusion (ablation) | Late fusion · DukeMTMC test | MAE: 1.43 -> 1.27 | Helped |
| add projection normalization to late fusion (ablation) | Late fusion · City Street test | MAE: 9.87 -> 8.12 | Helped |
| use learnable rather than fixed scale selection (ablation) | MVMS · PETS2009 test | MAE: 3.82 -> 3.49 | Helped |
| use learnable rather than fixed scale selection (ablation) | MVMS · DukeMTMC test | MAE: 1.09 -> 1.03 | Helped |
| use learnable rather than fixed scale selection (ablation) | MVMS · City Street test | MAE: 7.80 -> 8.01 | Hurt |
| align feature scales across views before fusion | MVMS versus naïve early fusion · PETS2009 test | MAE: 5.43 -> 3.49 | Helped |
| align feature scales across views before fusion | MVMS versus naïve early fusion · DukeMTMC test | MAE: 1.25 -> 1.03 | Helped |
| align feature scales across views before fusion | MVMS versus naïve early fusion · City Street test | MAE: 8.10 -> 8.01 | Helped |
Closest papers by meaning
- 3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels (AAAI 2020 · similarity 0.95)
- Switching Convolutional Neural Network for Crowd Counting (CVPR 2017 · similarity 0.91)
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (CVPR 2016 · similarity 0.91)
- Context-Aware Crowd Counting (CVPR 2019 · similarity 0.91)
- Cross-View Cross-Scene Multi-View Crowd Counting (CVPR 2021 · similarity 0.90)
- Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (CVPR 2019 · similarity 0.90)
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.