Crowd Counting On Ucf Cc 50

Metrics

MAE

Results

Performance results of various models on this benchmark

Model Name	MAE	Paper Title	Repository
LSC-CNN	225.6	Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
ic-CNN	260.9	Iterative Crowd Counting	-
Idrees et al.	419.5	Multi-source Multi-scale Counting in Extremely Dense Crowd Images	-
M-SFANet	162.33	Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting
Liu et al.	337.6	Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
SGANet	224.6	Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss
ACSCP	291.0	Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
SGANet + CL	221.9	Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss
CSRNet	266.1	CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
SPANet	232.6	Learning Spatial Awareness to Improve Crowd Counting	-
CP-CNN	295.8	Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs	-
Zhang et al.	467.0	Cross-Scene Crowd Counting via Deep Convolutional Neural Networks	-
Cascaded-MTL	322.8	CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
Switch-CNN	318.1	Switching Convolutional Neural Network for Crowd Counting
APGCC	154.8	Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance
MCNN	377.6	Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
CAN	212.2	Context-Aware Crowd Counting
GauNet (ResNet-50)	186.3	Rethinking Spatial Invariance of Convolutional Networks for Object Counting
SANet	258.4	Scale Aggregation Network for Accurate and Efficient Crowd Counting
IG-CNN	291.4	Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN	-

0 of 22 row(s) selected.