Related papers: Multi-scale Feature Aggregation for Crowd Counting

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most…

In the context of crowd counting, most of the works have focused on improving the accuracy without regard to the performance leading to algorithms that are not suitable for embedded applications. In this paper, we propose a lightweight…

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…

Convolutional neural networks (CNNs) and their variations have shown effectiveness in facial expression recognition (FER). However, they face challenges when dealing with high computational complexity and multi-view head poses in real-world…

Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e.g. persons) in images. The perspective effect, which significantly influences the distribution of data points, plays an important role in…

Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…

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…

The task of instance segmentation in remote sensing images, aiming at performing per-pixel labeling of objects at instance level, is of great importance for various civil applications. Despite previous successes, most existing instance…

Despite the advances in the field of Face Recognition (FR), the precision of these methods is not yet sufficient. To improve the FR performance, this paper proposes a technique to aggregate the outputs of two state-of-the-art (SOTA) deep FR…

Crowd counting, for estimating the number of people in a crowd using vision-based computer techniques, has attracted much interest in the research community. Although many attempts have been reported, real-world problems, such as huge…

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…

Crowd counting is a challenging problem due to the scene complexity and scale variation. Although deep learning has achieved great improvement in crowd counting, scene complexity affects the judgement of these methods and they usually…

Crowd counting in single-view images has achieved outstanding performance on existing counting datasets. However, single-view counting is not applicable to large and wide scenes (e.g., public parks, long subway platforms, or event spaces)…

Object detection in aerial imagery is a critical task in applications such as UAV reconnaissance. Although existing methods have extensively explored feature interaction between different modalities, they commonly rely on simple fusion…

Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation. However, most of the current popular network…

Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). An essential part of the ViG framework is the node-neighbor…

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…

Deepfake detection faces increasing challenges since the fast growth of generative models in developing massive and diverse Deepfake technologies. Recent advances rely on introducing heuristic features from spatial or frequency domains…

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…