P2PNet

Reported on 3 benchmarks across 1 task · 2 papers · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

CrowdsonDroneRGBT
10.83· 2025-05-11
1
SOTA
Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network arXiv:2505.06937
CrowdsonShanghaiTech A
MAE· 2021-07-27
52.74
best: 47.81 (EBC-ZIP-B)
SOTA
Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework arXiv:2107.12746
CrowdsonShanghaiTech A
MSE· 2021-07-27
85.06
best: 76.7 (APGCC)
SOTA
Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework arXiv:2107.12746