Research map / Architectures and efficiency / Attention and transformers
Attentional Neural Fields for Crowd Counting
Anran Zhang, Lei Yue, Jiayi Shen, Fan Zhu, Xiantong Zhen, Xianbin Cao, Ling Shao
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 inter- and intra-layer attentions to the CRF baseline (ablation) | ANF baseline · ShanghaiTech Part A | MAE: 66.2 -> 63.9 | Improved |
| add inter- and intra-layer attentions to the CRF baseline (ablation) | ANF baseline · ShanghaiTech Part A | MSE: 110.8 -> 99.4 | Improved |
| use ANF instead of SANet | SANet · UCF-CC-50 | MSE: 334.9 -> 340.0 | Hurt |
| use ANF instead of SANet | SANet · UCF-CC-50 | MAE: 258.4 -> 250.2 | Improved |
| use ANF instead of Idrees et al. | Idrees et al. · UCF-QNRF | MAE: 132 -> 110 | Improved |
| use ANF instead of SANet | SANet · WorldExpo 10 Scene 3 | MAE: 9.0 -> 15.1 | Hurt |
| use ANF instead of CSRNet | CSRNet · ShanghaiTech Part A (model size) | # parameters: 16.26M -> 7.9M | Improved |
Closest papers by meaning
- Attention Scaling for Crowd Counting (CVPR 2020 · similarity 0.90)
- Context-Aware Crowd Counting (CVPR 2019 · similarity 0.89)
- Boosting Crowd Counting via Multifaceted Attention (CVPR 2022 · similarity 0.89)
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (CVPR 2016 · similarity 0.89)
- Shallow Feature Based Dense Attention Network for Crowd Counting (AAAI 2020 · similarity 0.88)
- Gramformer: Learning Crowd Counting via Graph-Modulated Transformer (AAAI 2024 · similarity 0.87)
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.
