Frequency-selective countnet: Enhancing text-guided object counting with frequency features

Cheng Qian

doi:10.1016/j.patrec.2025.12.014

Frequency-selective countnet: Enhancing text-guided object counting with frequency features

2026-01-21

0

PRE

AI

DOI：10.1016/j.patrec.2025.12.014

原文链接

摘要

En 中文

Text-guided object counting aims to estimate the number of objects described by natural language within complex visual scenes. However, existing approaches often struggle to align textual intent with diverse visual patterns, especially when target objects vary in scale, appearance, or context. To address these limitations, we propose Frequency-Selective CountNet (FSCNet), a novel framework that integrates spatial and frequency-domain features for precise text-guided counting. FSCNet introduces a Triple-Stream Attention Fusion Module (TSAFM) that combines textual, global, and local visual features. Additionally, an Adaptive Frequency Selector (AFS) dynamically emphasizes frequency components by separately modulating the magnitude and phase spectra, preserving geometric consistency during decoding. Extensive experiments on the FSC-147 and CARPK datasets demonstrate that FSCNet achieves state-of-the-art performance, outperforming previous best methods by 18.34% in MAE and 27.41% in RMSE on FSC-147 (Avg.) and by 5.17%/7.58% on CARPK.

Keyword:

Object counting

Vision-Language model

Frequency domain

Multimodal fusion

Frequency-selective countnet: Enhancing text-guided object counting with frequency features

摘要

期刊

机构

引用论文