AI Paper Atlas

Research map / 3D vision / Depth and stereo

Adaptive Density Map Generation for Crowd Counting

Jia Wan, Antoni Chan

ICCV 2019 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 183 citations (OpenAlex)

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 changedWhereMeasuredEffect
add density map refinement (adaptive-kernel maps)CSRNet · ShanghaiTech AMAE: 66.4 -> 64.2Improved
add density map refinement (fixed-kernel maps)MCNN · ShanghaiTech AMAE: 95.4 -> 102.3Hurt
add density map refinement (adaptive-kernel maps)MCNN · ShanghaiTech AMAE: 103.3 -> 96.7Improved
add density map refinement (fixed kernel)FCN · ShanghaiTech BMAE: 18.8 -> 15.2Improved
add jointly trained generator instead of fixed sigma=16 kernelSFCN · ShanghaiTech AMAE: 70.8 -> 68.4Improved
add jointly trained generator instead of adaptive kernelCSRNet · ShanghaiTech BMAE: 10.6 -> 8.1Improved
add jointly trained generator instead of fixed sigma=16 kernelMCNN · ShanghaiTech BMAE: 18.7 -> 17.7No clear effect
add jointly trained generator instead of fixed sigma=4 kernelFCN · ShanghaiTech BMAE: 13.8 -> 13.9No clear effect
add global count loss instead of local spatial loss (ablation)density map generator · ShanghaiTech AMAE: 68.8 -> 64.7Improved
add global count loss instead of hard normalization (ablation)density map generator · ShanghaiTech AMAE: 112.8 -> 64.7Improved
use fixed instead of learnable initial Gaussian kernels (ablation)density map generator · ShanghaiTech AMAE: 74.7 -> 64.7Improved
add self-attention instead of image-based attention (ablation)density map generator · ShanghaiTech AMAE: 66.9 -> 64.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy