Research map / Image generation / Image restoration
Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method
Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel
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 residual learning to the base network (ablation) | CG-DRCN · JHU-CROWD | MAE: 81.1 -> 76.4 | Improved |
| add residual learning to the base network (ablation) | CG-DRCN · JHU-CROWD | MSE: 248.5 -> 218.6 | Improved |
| add confidence estimation blocks with lambda_c=0 (ablation) | CG-DRCN · JHU-CROWD | MAE: 76.4 -> 74.6 | Improved |
| add confidence estimation blocks with lambda_c=0 (ablation) | CG-DRCN · JHU-CROWD | MSE: 218.6 -> 215.5 | Improved |
| enable uncertainty-based confidence weighting (lambda_c=1 instead of 0) (ablation) | CG-DRCN · JHU-CROWD | MAE: 74.6 -> 66.1 | Improved |
| enable uncertainty-based confidence weighting (lambda_c=1 instead of 0) (ablation) | CG-DRCN · JHU-CROWD | MSE: 215.5 -> 195.5 | Improved |
| full CG-DRCN versus CSR-Net | CG-DRCN · JHU-CROWD | overall MAE: 78.4 -> 66.1 | Improved |
| full CG-DRCN versus SA-Net (patch-based) on Part-B | CG-DRCN · ShanghaiTech Part-B | MAE: 8.4 -> 8.5 | Mixed |
| full CG-DRCN versus Jian et al. on Part-A | CG-DRCN · ShanghaiTech Part-A | MAE: 64.2 -> 64.0 | Improved |
| full CG-DRCN versus Jian et al. | CG-DRCN · UCF-QNRF | MAE: 113.0 -> 112.2 | Improved |
Closest papers by meaning
- JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (TPAMI 2020 · similarity 0.97)
- Residual Regression With Semantic Prior for Crowd Counting (CVPR 2019 · similarity 0.92)
- Counting without Scale: Scale-Consistent Error Correction for Crowd Counting (NeurIPS 2026 · similarity 0.90)
- Iterative Crowd Counting (ECCV 2018 · similarity 0.90)
- Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (CVPR 2018 · similarity 0.89)
- Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (ECCV 2018 · similarity 0.89)
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.
