Salvato in:
Dettagli Bibliografici
Autori principali: Jung, Seoik, Song, Taekyung
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.08240
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918088866267136
author Jung, Seoik
Song, Taekyung
author_facet Jung, Seoik
Song, Taekyung
contents In this paper, we investigate the applicability of the CLIP-EBC framework, originally designed for crowd counting, to car object counting using the CARPK dataset. Experimental results show that our model achieves second-best performance compared to existing methods. In addition, we propose a K-means weighted clustering method to estimate object positions based on predicted density maps, indicating the framework's potential extension to localization tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08240
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
Jung, Seoik
Song, Taekyung
Computer Vision and Pattern Recognition
I.4.8; I.2.10
In this paper, we investigate the applicability of the CLIP-EBC framework, originally designed for crowd counting, to car object counting using the CARPK dataset. Experimental results show that our model achieves second-best performance compared to existing methods. In addition, we propose a K-means weighted clustering method to estimate object positions based on predicted density maps, indicating the framework's potential extension to localization tasks.
title Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
topic Computer Vision and Pattern Recognition
I.4.8; I.2.10
url https://arxiv.org/abs/2507.08240