Crowd Counting On Ucf Cc 50

Métriques

MAE

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	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.