Crowd Counting

71 papers with code • 6 benchmarks • 14 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

Latest papers without code

Direct Measure Matching for Crowd Counting

no code yet • 4 Jul 2021

Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.

Crowd Counting

Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting

no code yet • 23 Jun 2021

More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity.

Crowd Counting

A Generalized Loss Function for Crowd Counting and Localization

no code yet • CVPR 2021

In this paper, we investigate learning the density map representation through an unbalanced optimal transport problem, and propose a generalized loss function to learn density maps for crowd counting and localization.

Crowd Counting

Cross-View Cross-Scene Multi-View Crowd Counting

no code yet • CVPR 2021

Multi-view crowd counting has been previously proposed to utilize multi-cameras to extend the field-of-view of a single camera, capturing more people in the scene, and improve counting performance for occluded people or those in low resolution.

Crowd Counting

Hybrid attention network based on progressive embedding scale-context for crowd counting

no code yet • 4 Jun 2021

In this paper, we propose a Hybrid Attention Network (HAN) by employing Progressive Embedding Scale-context (PES) information, which enables the network to simultaneously suppress noise and adapt head scale variation.

Crowd Counting

Multi-Level Attentive Convoluntional Neural Network for Crowd Counting

no code yet • 24 May 2021

Recently the crowd counting has received more and more attention.

Crowd Counting

Boosting Crowd Counting with Transformers

no code yet • 23 May 2021

This indicates that global scene context is essential, despite the seemingly bottom-up nature of the problem.

Crowd Counting

Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification

no code yet • 20 May 2021

The classification branch extracts global group priors by learning correlations among image clusters.

Colorization Crowd Counting

Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead

no code yet • 19 May 2021

Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early exiting.

Audio Classification Crowd Counting +1

Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting

no code yet • 28 Apr 2021

Noting the scarcity and low quality (in terms of resolution and scene diversity) of the publicly available video crowd datasets, we have collected and built a large-scale video crowd counting datasets, VidCrowd, to contribute to the community.

Crowd Counting