HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Crowd Counting On Ucf Qnrf

Metrics

MAE

Results

Performance results of various models on this benchmark

Paper Title
Idrees et al.315Multi-source Multi-scale Counting in Extremely Dense Crowd Images
MCNN277Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Encoder-Decoder270SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Cascaded-MTL252CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
Switch-CNN228Switching Convolutional Neural Network for Crowd Counting
Resnet101190Deep Residual Learning for Image Recognition
Densenet201163Densely Connected Convolutional Networks
Idrees et al.132Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
CAN107Context-Aware Crowd Counting
SGANet89.1Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss
SGANet + CL87.6Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss
M-SFANet85.6Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting
DM-Count85.6Distribution Matching for Crowd Counting
PSL-Net85.5Crowd Counting and Individual Localization Using Pseudo Square Label
GauNet (ResNet-50)81.6Rethinking Spatial Invariance of Convolutional Networks for Object Counting
CLIP-EBC (ResNet50)80.5CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
CLIP-EBC (ViT-B/16)80.3CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
APGCC80.1Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance
CSRNet-EBC79.3CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
DMCount-EBC77.2CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
0 of 22 row(s) selected.
Crowd Counting On Ucf Qnrf | SOTA | HyperAI