paper-with-me

홈 › Papers

EHNet: An Efficient Hybrid Network for Crowd Counting and Localization

2025-03-15 · Yuqing Yan, Yirui Wu

In recent years, crowd counting and localization have become crucial techniques in computer vision, with applications spanning various domains. The presence of multi-scale crowd distributions within a single image remains a fundamental challenge in crowd counting tasks. To address these challenges, we introduce the Efficient Hybrid Network (EHNet), a novel framework for efficient crowd counting and localization. By reformulating crowd counting into a point regression framework, EHNet leverages the Spatial-Position Attention Module (SPAM) to capture comprehensive spatial contexts and long-range dependencies. Additionally, we develop an Adaptive Feature Aggregation Module (AFAM) to effectively fuse and harmonize multi-scale feature representations. Building upon these, we introduce the Multi-Scale Attentive Decoder (MSAD). Experimental results on four benchmark datasets demonstrate that EHNet achieves competitive performance with reduced computational overhead, outperforming existing methods on ShanghaiTech Part \_A, ShanghaiTech Part \_B, UCF-CC-50, and UCF-QNRF. Our code is in https://anonymous.4open.science/r/EHNet.

📄 PDF Abstract BibTeX arXiv:2503.12061

Code (0)

등록된 구현이 없습니다.

Tasks

Crowd CountingDecoder

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Hybrid Graph Neural Networks for Crowd Counting

2020-01-31 · Ao Luo, Fan Yang, Xin Li, Dong Nie 외

Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful informati…

Crowd CountingGraph Neural Network

Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization

2021-04-26 · Yi Wang, Xinyu Hou, Lap-Pui Chau

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-wis…

Crowd Counting

Multiscale Crowd Counting and Localization By Multitask Point Supervision

2022-02-21 · Mohsen Zand, Haleh Damirchi, Andrew Farley, Mahdiyar Molahasani 외

We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multita…

Crowd Counting

SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization

2026-03-25 · Qi Zhang, Daijie Chen, Yunfei Gong, Hui Huang arxiv

Existing multi-view crowd counting and localization methods are evaluated under relatively small scenes with limited crowd numbers, camera views, and frames. This makes the evaluation and comparison of existing methods i…

Data AugmentationCrowd Counting

A Generalized Loss Function for Crowd Counting and Localization

2021-06-19 · CVPR 2021 1 · Jia Wan, Ziquan Liu, Antoni B. Chan

Previous work shows that a better density map representation can improve the performance of crowd counting. In this paper, we investigate learning the density map representation through an unbalanced optimal transpor…

Crowd Counting