articleInternational Journal of Computer VisionJan 17, 2026Closed access

Large Foundation Model Empowered Region-aware Underwater Image Captioning

HLHuanyu LiLLLi LiHWHao WangWZWeibo ZhangPRPeng Ren

China University of Petroleum, East China · Laoshan Laboratory

Indexed incrossref

Abstract

No abstract available for this paper.

Citation impact

14
total citations
FWCI
355.63
Percentile
100%
References
43
Too recent for citation history.

Authors

5

Topics & keywords

Topics
Keywords
  • Closed captioning
  • Underwater
  • Feature (linguistics)
  • Feature extraction
  • Encoder
  • Process (computing)
  • Ambiguity
  • Object (grammar)
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.

Funding