3 papers
cs.CV2026
ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding
Junyi Hu, Tian Bai, Fengyi Wu +3
Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack fine-grained…
cs.CV2025
CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions
Yuchen Huang, Zhiyuan Fan, Zhitao He +3
Pretrained vision-language models (VLMs) such as CLIP excel in general multimodal comprehension but often struggle to capture nuanced, context-dependent visual cues. This makes it…
cs.CL2025
Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation
Li Zhou, Lutong Yu, Dongchu Xie +3
Culture is a rich and dynamic domain that evolves across both geography and time. However, existing studies on cultural understanding with vision-language models (VLMs) primarily e…