Related papers: FSCA-Net: Feature-Separated Cross-Attention Networ…

Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered. Attention mechanisms have…

The paper focuses on improving the recent plug-and-play patch rescaling module (PRM) based approaches for crowd counting. In order to make full use of the PRM potential and obtain more reliable and accurate results for challenging images…

Perspective distortions and crowd variations make crowd counting a challenging task in computer vision. To tackle it, many previous works have used multi-scale architecture in deep neural networks (DNNs). Multi-scale branches can be either…

In this paper, we propose a simple yet effective crowd counting and localization network named SCALNet. Unlike most existing works that separate the counting and localization tasks, we consider those tasks as a pixel-wise dense prediction…

Crowd counting is one of the core tasks in various surveillance applications. A practical system involves estimating accurate head counts in dynamic scenarios under different lightning, camera perspective and occlusion states. Previous…

We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale…

Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting. With the ubiquitous video capture devices in public safety field, how to…

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes…

Self-training crowd counting has not been attentively explored though it is one of the important challenges in computer vision. In practice, the fully supervised methods usually require an intensive resource of manual annotation. In order…

RGB-Thermal (T) crowd counting aims to integrate visible-spectrum and thermal infrared information to improve the robustness of crowd density estimation in complex scenes. Although existing studies generally improve counting accuracy…

For pixel-level crowd understanding, it is time-consuming and laborious in data collection and annotation. Some domain adaptation algorithms try to liberate it by training models with synthetic data, and the results in some recent works…

Multi-view compression technology, especially Stereo Image Compression (SIC), plays a crucial role in car-mounted cameras and 3D-related applications. Interestingly, the Distributed Source Coding (DSC) theory suggests that efficient data…

Accurate RGB-Thermal (RGB-T) crowd counting is crucial for public safety in challenging conditions. While recent Transformer-based methods excel at capturing global context, their inherent lack of spatial inductive bias causes attention to…

Multi-task learning improves generalization performance by sharing knowledge among related tasks. Existing models are for task combinations annotated on the same dataset, while there are cases where multiple datasets are available for each…

Unsupervised Domain Adaptation (UDA) seeks to transfer knowledge from a labeled source domain to an unlabeled target domain but often suffers from severe domain and scale gaps that degrade performance. Existing cross-attention-based…

This paper focuses on the challenging crowd counting task. As large-scale variations often exist within crowd images, neither fixed-size convolution kernel of CNN nor fixed-size attention of recent vision transformers can well handle this…

Automatic crowd behaviour analysis is an important task for intelligent transportation systems to enable effective flow control and dynamic route planning for varying road participants. Crowd counting is one of the keys to automatic crowd…

Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…

In this paper, we present a novel method Coarse- and Fine-grained Attention Network (CFANet) for generating high-quality crowd density maps and people count estimation by incorporating attention maps to better focus on the crowd area. We…

Crowd counting is an important yet challenging task in computer vision due to serious occlusions, complex background and large scale variations, etc. Multi-column architecture is widely adopted to overcome these challenges, yielding…