IconoBench: Can VLMs Understand Cultural Symbols and Iconography?
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3-12
Abstract
No abstract availableThis publication has 25 references indexed in Scilit:
- Dual-granularity image-text alignment for zero-shot composed image retrievalExpert Systems with Applications, 2026
- R3-RAG: Reweight, rerank, and reflect for evidence-calibrated scientific multimodal reasoningExpert Systems with Applications, 2026
- Dual-Image vision–language framework with expert knowledge for automated fine-grained mint-state coin gradingExpert Systems with Applications, 2026
- Large language model enhanced image caption for Chinese cultural relicsExpert Systems with Applications, 2026
- Parameter-efficient transfer for CLIP-based text-to-person retrievalSignal Processing: Image Communication, 2026
- Responsible AI in healthcare: Mitigating hallucinations and enhancing multimodal fusion - based reasoning in medical imagingInformation Fusion, 2026
- Retrieval-augmented in-context learning for multimodal large language models in disease classificationJournal of Biomedical Informatics, 2026
- Multi-label sewer defect classification based on CLIP with fine-to-coarse contextual representationsAdvanced Engineering Informatics, 2026
- Multimodal hierarchical classification using cascade-of-thoughtInformation Processing & Management, 2025
- Towards accurate and scalable cross-modal retrieval with a distillation approachExpert Systems with Applications, 2025