STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918468035543040 |
|---|---|
| author | Gong, Yanpei Zhang, Beichen Wang, Hao Qi, Zhaobo Liu, Xinyan Xu, Yuanrong Gao, Ruiyang Zhang, Weigang |
| author_facet | Gong, Yanpei Zhang, Beichen Wang, Hao Qi, Zhaobo Liu, Xinyan Xu, Yuanrong Gao, Ruiyang Zhang, Weigang |
| contents | Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored video modeling, they largely overlook the inherent ambiguities in viewpoint, scale, and prior knowledge, lacking effective constraints on the encoder. In this paper, we present STAND, a Semantic Anchoring Constraint with Dual-Granularity Disambiguation for RSICC, to progressively resolve these ambiguities. Specifically, to establish a reliable feature foundation, we first introduce an interpretable constraint to regularize temporal representations. Operating on these purified features, a dual-granularity disambiguation module resolves spatial uncertainties by coupling macro-level global context aggregation for viewpoint confusion with micro-level frequency-refocused attention for small-object scale enhancement. Ultimately, to translate these visually disambiguated features into precise text, a semantic concept anchoring module leverages language categorical priors to tackle knowledge ambiguity during decoding. Extensive experiments verify the superiority of STAND and its effectiveness in addressing ambiguities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23309 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning Gong, Yanpei Zhang, Beichen Wang, Hao Qi, Zhaobo Liu, Xinyan Xu, Yuanrong Gao, Ruiyang Zhang, Weigang Computer Vision and Pattern Recognition Machine Learning Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored video modeling, they largely overlook the inherent ambiguities in viewpoint, scale, and prior knowledge, lacking effective constraints on the encoder. In this paper, we present STAND, a Semantic Anchoring Constraint with Dual-Granularity Disambiguation for RSICC, to progressively resolve these ambiguities. Specifically, to establish a reliable feature foundation, we first introduce an interpretable constraint to regularize temporal representations. Operating on these purified features, a dual-granularity disambiguation module resolves spatial uncertainties by coupling macro-level global context aggregation for viewpoint confusion with micro-level frequency-refocused attention for small-object scale enhancement. Ultimately, to translate these visually disambiguated features into precise text, a semantic concept anchoring module leverages language categorical priors to tackle knowledge ambiguity during decoding. Extensive experiments verify the superiority of STAND and its effectiveness in addressing ambiguities. |
| title | STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.23309 |