A multi-scale information fusion framework with interaction-aware global attention for industrial vision anomaly detection and localization DOI
Zhuo Li, Yifei Ge, Lin Meng

и другие.

Information Fusion, Год журнала: 2025, Номер unknown, С. 103356 - 103356

Опубликована: Июнь 1, 2025

Язык: Английский

Oil Spill Drift Prediction Enhanced by Correcting Numerically Forecasted Sea Surface Dynamic Fields with Adversarial Temporal Convolutional Networks DOI
Peng Ren, Qing Jia, Qing Xu

и другие.

IEEE Transactions on Geoscience and Remote Sensing, Год журнала: 2025, Номер 63, С. 1 - 18

Опубликована: Янв. 1, 2025

Timely and accurate representation of sea surface dynamic fields is crucial for oil spill drift prediction. Numerically forecasted are available in a timely manner, but their accuracy limited. Conversely, reanalysis offer superior suffer from time delays. To enhance the performance prediction, we propose deep learning-based approach to correcting numerically fields, aligning them more closely with fields. Our introduces an adversarial temporal convolutional network (ATCN) framework, consisting (TCN)-based corrector discriminator. The TCN can characterize field sequences both spatially temporally. In this scenario, processes outputs corrected that approximate Adversarial training discriminator further refines corrector. This enhances prediction using We also provide dataset drifts Symphony Sanchi accidents, including related data remote sensing data, establishing baseline evaluating Experiments on validate ATCN framework's effectiveness enhancing

Язык: Английский

Процитировано

5
Confucius tri-learning: A paradigm of learning from both good examples and bad examples DOI
Peng Ren, Zongjun Han, Zhiqiang Yu

и другие.

Pattern Recognition, Год журнала: 2025, Номер unknown, С. 111481 - 111481

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

4
Image inpainting via Multi-scale Adaptive Priors DOI

Yufeng Wang,

Dongsheng Guo,

Haoru Zhao

и другие.

Pattern Recognition, Год журнала: 2025, Номер unknown, С. 111410 - 111410

Опубликована: Янв. 1, 2025

Процитировано

1
An underwater acoustic semantic communication approach to underwater image transmission DOI Creative Commons

Ying Zhang,

Huanyu Li, Bingyu Li

и другие.

Intelligent Marine Technology and Systems, Год журнала: 2025, Номер 3(1)

Опубликована: Фев. 25, 2025

Язык: Английский

Процитировано

1
Underwater image captioning via attention mechanism based fusion of visual and textual information DOI
Li Li, Huanyu Li, Peng Ren

и другие.

Information Fusion, Год журнала: 2025, Номер 123, С. 103269 - 103269

Опубликована: Май 5, 2025

Язык: Английский

Процитировано

0
A vision-language foundation model-based multi-modal retrieval-augmented generation framework for remote sensing lithological recognition DOI
Xiaodao Chen,

Yupeng Liu,

Wei Han

и другие.

ISPRS Journal of Photogrammetry and Remote Sensing, Год журнала: 2025, Номер 225, С. 328 - 340

Опубликована: Май 9, 2025

Язык: Английский

Процитировано

0
Water-Adapted 3D Gaussian Splatting for precise underwater scene reconstruction DOI Creative Commons
Xinnan Fan, Xiaotian Wang,

Hong Ni

и другие.

Frontiers in Marine Science, Год журнала: 2025, Номер 12

Опубликована: Май 16, 2025

Underwater 3D reconstruction is essential for marine surveying, ecological protection, and underwater engineering. Traditional methods, designed air environments, fail to account optical properties, leading poor detail retention, color reproduction, visual consistency. In recent years, Gaussian Splatting (3DGS) has emerged as an efficient alternative, offering improvements in both speed quality. However, existing 3DGS methods struggle adaptively adjust point distribution based on scene complexity, often resulting inadequate complex areas inefficient resource usage simpler ones. Additionally, depth variations scenes affect image clarity, current lack adaptive depth-based rendering, inconsistent clarity between near distant objects. Existing loss functions, primarily address challenges such distortion structural differences. To these challenges, we propose improved method combining complexity-adaptive distribution, depth-adaptive multi-scale radius a tailored function environments. Our enhances accuracy Experimental results static dynamic datasets show significant rendering accuracy, stability compared traditional making it suitable practical applications.

Язык: Английский

Процитировано

0
The knowledge distillation-assisted multimodal model for osteoporosis screening DOI
Teng Su, Qing Yang,

Meng Si

и другие.

Computer Methods and Programs in Biomedicine, Год журнала: 2025, Номер unknown, С. 108848 - 108848

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
SEAUNet: a novel edge-adaptive attention based UNet for sonar image segmentation DOI

G Divyabarathi,

Gayathri Soman,

P. V. Sabeen Govind

и другие.

Signal Image and Video Processing, Год журнала: 2025, Номер 19(8)

Опубликована: Май 28, 2025

Язык: Английский

Процитировано

0
Underwater image color correction via global and local two-step optimization DOI

Baiqiang Yu,

Ling Zhou,

Wenqiang Yu

и другие.

Pattern Recognition Letters, Год журнала: 2025, Номер unknown

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0