Salvato in:
Dettagli Bibliografici
Autori principali: Yan, Yuqing, Wu, Yirui
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.12061
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912276874788864
author Yan, Yuqing
Wu, Yirui
author_facet Yan, Yuqing
Wu, Yirui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EHNet: An Efficient Hybrid Network for Crowd Counting and Localization
Yan, Yuqing
Wu, Yirui
Computer Vision and Pattern Recognition
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.
title EHNet: An Efficient Hybrid Network for Crowd Counting and Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.12061