computer-vision-7
Crowd Counting
3260 papers • 126 benchmarks • 313 datasets
Crowd Counting is a task to count people in image. It is mainly used in real-life for automated public monitoring such as surveillance and traffic control. Different from object detection, Crowd Counting aims at recognizing arbitrarily sized targets in various situations including sparse and cluttering scenes at the same time. Source: Deep Density-aware Count Regressor
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in crowd-counting-7
Trend
Dataset
Best Model
Actions
ShanghaiTech A
ShanghaiTech A
ShanghaiTech B
ShanghaiTech B
UCF CC 50
UCF CC 50
Libraries
iUse these libraries to find crowd-counting-7 models and implementations
3 papers 2,926
Datasets
Subtasks
No subtasks available.
Most implemented papers
Densely Connected Convolutional Networks
Kilian Q. Weinberger, Zhuang Liu, Gao Huang•Wed Aug 24 2016
The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
41544
