IEEE Transactions on Geoscience and Remote Sensing · 2025 · 28 citations · 59 references
ComputingOcean EngineeringComputer VisionRobot PerceptionSensor FusionFeature-level FusionImage FusionObject RecognitionUnderwater PerceptionAttention-based FusionAttention-based Image FusionImage Feature FusionMulti-scale Feature RepresentationSemantic Scene UnderstandingUnderwater Image EnhancementUnderwater Scene UnderstandingVisual Scene Understanding
Underwater image captioning bridges the gap between visual perception and semantic understanding of underwater scenes, playing a crucial role in applications such as ocean geoscience and underwater remote sensing. Despite progress in this field, limitations remain in achieving accurate underwater image captioning. The main limitations are: (a) the underestimation of basic sketch features in underwater image captioning, and (b) insufficient consideration of the impact of scale differences in underwater objects. To overcome these limitations, we propose underwater image captioning with AquaSketch enhanced cross-scale information fusion. Our novel contributions are twofold: (a) A novel AquaSketch (i.e., aqua sketch) enhancement method is developed to reduce the impact of underwater image distortion on scene understanding, while enhancing both detailed and background information; and (b) A top-down dual-branch pyramid for cross-scale information fusion is proposed. This architecture fuses multi-scale feature information from two branches through an attention-based feature fusion structure, performing cross-scale fusion in a top-down manner. The resulting pyramid fusion features offer a comprehensive representation of underwater object information. Collectively, these contributions facilitate the generation of accurate and comprehensive underwater image captions. Experimental evaluations on three datasets demonstrate that our proposed underwater image captioning model achieves state-of-the-art performance in the field.
59
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
Xception: Deep Learning with Depthwise Separable Convolutions
François Chollet · 2017 · 19K citations
Show and tell: A neural image caption generator
Oriol Vinyals, Alexander Toshev, Samy Bengio et al. · 2015 · 6.4K citations
Long-term recurrent convolutional networks for visual recognition and description
Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama et al. · 2015 · 5.3K citations