Cross-domain zero-shot semantic segmentation for unstructured environments via EVA-CLIP model, ensemble prompt engineering, and optimized text-image matching

• Nana Zhou ,

  Roles Conceptualization, Funding acquisition, Methodology, Visualization, Writing – original draft

  * E-mail: zhounana@sdxiehe.edu.cn

  Affiliation School of Computer Science, Shandong Xiehe University, Shandong, China

  https://orcid.org/0009-0005-6796-5872

  ⨯
• Xianhua Zhao,

  Roles Conceptualization, Validation, Visualization

  Affiliation Jinan Energy Investment Holding Group Co., Ltd., Shandong, China

  ⨯
• Fengjun Zhou,

  Roles Resources, Supervision, Validation

  Affiliation School of Computer Science, Shandong Xiehe University, Shandong, China

  ⨯
• Ji Li,

  Roles Investigation, Methodology

  Affiliation School of Computer Science, Shandong Xiehe University, Shandong, China

  ⨯
• Xiuming Yue

  Roles Investigation, Writing – review & editing

  Affiliation School of Computer Science, Shandong Xiehe University, Shandong, China

  ⨯