Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
2025-07-11Code Available0· sign in to hype
Seoik Jung, Taekyung Song
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/jungseoik/CLIP-LOCAROfficialnone★ 1
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| CARPK | CLIP-LOCAR | MAE | 4.01 | — | Unverified |