Zhang qingli -, Wei Hu, Peng Ren, Haoqiang Tian, Chengqing Ruan, Yanchen Song · Journal of Marine Science and Engineering 2026 · 2026
DOI: 10.3390/jmse14201888
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Accurate visibility information under sea fog or low-visibility conditions is essential for ensuring navigational safety in ports and nearshore waters. This study combines single-frame images extracted from nearshore sea fog observation videos with synchronized meteorological variables to investigate sea fog visibility estimation and develops the ConvNeXt-MS-WDFM model. The model employs feature-wise linear modulation (FiLM) to modulate visual features using meteorological information and further integrates visual and meteorological information through Transformer-based cross-modal modeling. Experimental results show that ConvNeXt-MS-WDFM achieves
No comments yet — start the discussion below.