Research map / Architectures and efficiency / CNN design
Context-Aware Crowd Counting
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 |
|---|---|---|---|
| Adaptively combine multi-scale contextual features at each image location (ablation) | Context-Aware Network · ShanghaiTech Part A | MAE: 68.0 -> 62.3 | Helped |
| Add multi-scale contextual features rather than using only base features (ablation) | Context-Aware Network · ShanghaiTech Part A | MAE: 68.0 -> 63.4 | Helped |
| Weight scale-aware features instead of concatenating them (ablation) | Context-Aware Network · ShanghaiTech Part A | MAE: 63.4 -> 62.3 | Helped |
| Use contrast features to predict scale weights instead of scale features (ablation) | Context-Aware Network · ShanghaiTech Part A | MAE: 63.1 -> 62.3 | Helped |
| Add 1x1 channel-mixing convolutions after spatial pyramid pooling (ablation) | Context-Aware Network · Crowd-counting experiments | performance | Helped |
| Provide perspective-map geometry to guide contextual scale weighting | Context-Aware Network · Venice | MAE: 23.5 -> 20.5 | Helped |
| Provide perspective-map geometry to guide contextual scale weighting | Context-Aware Network · WorldExpo'10 average | MAE: 7.4 -> 7.2 | Helped |
Closest papers by meaning
- Switching Convolutional Neural Network for Crowd Counting (CVPR 2017 · similarity 0.91)
- Top-Down Feedback for Crowd Counting Convolutional Neural Network (AAAI 2018 · similarity 0.91)
- Divide and Grow: Capturing Huge Diversity in Crowd Images With Incrementally Growing CNN (CVPR 2018 · similarity 0.91)
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (CVPR 2016 · similarity 0.91)
- Leveraging Self-Supervision for Cross-Domain Crowd Counting (CVPR 2022 · similarity 0.91)
- Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs (CVPR 2019 · similarity 0.91)
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.