A Sketch+Text Composed Image Retrieval Dataset for Thangka
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917416772042752 |
|---|---|
| author | Xu, Jinyu Sun, Yi Zhang, Jiangling Xie, Qing Ji, Daomin Bao, Zhifeng Li, Jiachen Ma, Yanchun Liu, Yongjian |
| author_facet | Xu, Jinyu Sun, Yi Zhang, Jiangling Xie, Qing Ji, Daomin Bao, Zhifeng Li, Jiachen Ma, Yanchun Liu, Yongjian |
| contents | Composed Image Retrieval (CIR) enables image retrieval by combining multiple query modalities, but existing benchmarks predominantly focus on general-domain imagery and rely on reference images with short textual modifications. As a result, they provide limited support for retrieval scenarios that require fine-grained semantic reasoning, structured visual understanding, and domain-specific knowledge. In this work, we introduce CIRThan, a sketch+text Composed Image Retrieval dataset for Thangka imagery, a culturally grounded and knowledge-specific visual domain characterized by complex structures, dense symbolic elements, and domain-dependent semantic conventions. CIRThan contains 2,287 high-quality Thangka images, each paired with a human-drawn sketch and hierarchical textual descriptions at three semantic levels, enabling composed queries that jointly express structural intent and multi-level semantic specification. We provide standardized data splits, comprehensive dataset analysis, and benchmark evaluations of representative supervised and zero-shot CIR methods. Experimental results reveal that existing CIR approaches, largely developed for general-domain imagery, struggle to effectively align sketch-based abstractions and hierarchical textual semantics with fine-grained Thangka images, particularly without in-domain supervision. We believe CIRThan offers a valuable benchmark for advancing sketch+text CIR, hierarchical semantic modeling, and multimodal retrieval in cultural heritage and other knowledge-specific visual domains. The dataset is publicly available at https://github.com/jinyuxu-whut/CIRThan. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08411 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Sketch+Text Composed Image Retrieval Dataset for Thangka Xu, Jinyu Sun, Yi Zhang, Jiangling Xie, Qing Ji, Daomin Bao, Zhifeng Li, Jiachen Ma, Yanchun Liu, Yongjian Information Retrieval Composed Image Retrieval (CIR) enables image retrieval by combining multiple query modalities, but existing benchmarks predominantly focus on general-domain imagery and rely on reference images with short textual modifications. As a result, they provide limited support for retrieval scenarios that require fine-grained semantic reasoning, structured visual understanding, and domain-specific knowledge. In this work, we introduce CIRThan, a sketch+text Composed Image Retrieval dataset for Thangka imagery, a culturally grounded and knowledge-specific visual domain characterized by complex structures, dense symbolic elements, and domain-dependent semantic conventions. CIRThan contains 2,287 high-quality Thangka images, each paired with a human-drawn sketch and hierarchical textual descriptions at three semantic levels, enabling composed queries that jointly express structural intent and multi-level semantic specification. We provide standardized data splits, comprehensive dataset analysis, and benchmark evaluations of representative supervised and zero-shot CIR methods. Experimental results reveal that existing CIR approaches, largely developed for general-domain imagery, struggle to effectively align sketch-based abstractions and hierarchical textual semantics with fine-grained Thangka images, particularly without in-domain supervision. We believe CIRThan offers a valuable benchmark for advancing sketch+text CIR, hierarchical semantic modeling, and multimodal retrieval in cultural heritage and other knowledge-specific visual domains. The dataset is publicly available at https://github.com/jinyuxu-whut/CIRThan. |
| title | A Sketch+Text Composed Image Retrieval Dataset for Thangka |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2602.08411 |