Towards Noisy-Reference Paragraph Change Captioning: A Weakly Supervised Detection-Guided Historical-Cascaded Network for Remote-Sensing Images
Remote Sensing · 29.10.2026 · 18 (21) · 3732
DOI: 10.3390/rs18213732 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 29.10.2026. Verfasst von Qingming Chen und 5 weiteren Autor:innen. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province, Fujian Province Science and Technology Guiding Project.
Abstract (Originalsprache)
Remote-sensing image change captioning (RSICC) generally assumes correctly paired bitemporal images and focuses on isolated sentence descriptions, limiting applicability to archives where the correct temporal counterpart may be unknown. We introduce the Noisy-Reference Paragraph-Level Change-Captioning (NRP-CC) task, which requires retrieving the post-change observation from a noisy candidate pool before generating a coherent multi-statement paragraph. We construct the SECOND-ParCap dataset with image-level semantic annotations and paragraph-level change descriptions, and propose a Weakly Supervised Detection-Guided Historical-Cascaded Network (WSDHC-Net). WSDHC-Net leverages Dual Similarity Matching (DS-Matching) for retrieval from noisy candidate pools and employs weakly supervised detection to mine semantic cues for the Historical-Cascaded Paragraph Refinement Change-Captioning (HCPR-CC) module, which generates multi-statement paragraphs describing scene changes. We further introduce SA-ROUGE to evaluate sentence-level correspondence across the generated statements. On SECOND-ParCap, WSDHC-Net achieves Acc@1 scores of 99.53%, 99.29%, and 98.52% under appearance-hard retrieval with 5, 10, and 20 candidates, respectively. In a separate captioning benchmark using identical frozen retrieved inputs across all compared methods, WSDHC-Net attains ROUGE-L and SA-ROUGE scores of 0.5017 and 0.5016, respectively, under reference-assisted sentence-level evaluation; the corresponding paragraph-level scores are 0.2749 and 1.9305. These results support the feasibility of integrating temporal-correspondence retrieval with paragraph-level change description in NRP-CC.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Fujian Province
- Fujian Province Science and Technology Guiding Project
Zitieren
APA
Chen, Q., Chen, L., Chen, Y., Xie, Z., Fang, K., & Yang, K. (2026). Towards Noisy-Reference Paragraph Change Captioning: A Weakly Supervised Detection-Guided Historical-Cascaded Network for Remote-Sensing Images. Remote Sensing, 18(21), 3732. https://doi.org/10.3390/rs18213732
Vancouver
Chen Q, Chen L, Chen Y, Xie Z, Fang K, Yang K. Towards Noisy-Reference Paragraph Change Captioning: A Weakly Supervised Detection-Guided Historical-Cascaded Network for Remote-Sensing Images. Remote Sensing. 2026;18(21):3732. doi:10.3390/rs18213732
BibTeX
@article{Chen2026,
author = {Chen, Qingming and Chen, Lvhao and Chen, Yaoliang and Xie, Zhijian and Fang, Keyan and Yang, Kunping},
title = {Towards Noisy-Reference Paragraph Change Captioning: A Weakly Supervised Detection-Guided Historical-Cascaded Network for Remote-Sensing Images},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {21},
pages = {3732},
doi = {10.3390/rs18213732}
}
EUVIMED