FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385539485> ?p ?o ?g. }

• W4385539485 endingPage "106743" @default.
• W4385539485 startingPage "106743" @default.
• W4385539485 abstract "In recent years, underwater image enhancement and restoration technologies have become increasingly important in order to optimize the efficiency of maritime operations and promote the automatic machine learning of the maritime industry. A new hierarchical attention aggregation with multi-resolution feature learning for GAN-based underwater image enhancement is proposed to address the problems of color bias, underexposure, and blurring in underwater images. The proposed method consists of a generator and a discriminator. Specifically, the generator includes an encoder, a bottleneck layer, and a decoder. Generator introduces inter-block serial connections for better adaptation to complex image scenes and task requirements, and parallel connections to extract multi-level features and enhance the expressive capacity of the network. To extract semantic and contextual information, hierarchical attention dense aggregation is designed in the encoder, which includes multi-scale feature hierarchy and dense feature hierarchy. Additionally, a multi-scale spatial attention mechanism is designed in the bottleneck layer to handle variations in underwater image scenes. In the decoder, the feature channel layer is emphasized, and a multi-channel attention mechanism is proposed to restore the multi-resolution channel features to a three-channel enhanced image. Furthermore, the angular loss function is introduced as additional supervision, which improves the similarity between the generated and original images, increases image clarity, and reduces color bias. Meanwhile, we employ the patch discriminator to enhance machine vision. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art methods." @default.
• W4385539485 created "2023-08-04" @default.
• W4385539485 creator A5014950380 @default.
• W4385539485 creator A5039022693 @default.
• W4385539485 creator A5043228449 @default.
• W4385539485 creator A5051197631 @default.
• W4385539485 creator A5086616733 @default.
• W4385539485 creator A5090724385 @default.
• W4385539485 date "2023-10-01" @default.
• W4385539485 modified "2023-09-24" @default.
• W4385539485 title "Hierarchical attention aggregation with multi-resolution feature learning for GAN-based underwater image enhancement" @default.
• W4385539485 cites W2015196405 @default.
• W4385539485 cites W2141983208 @default.
• W4385539485 cites W2794405642 @default.
• W4385539485 cites W2890234995 @default.
• W4385539485 cites W2901081703 @default.
• W4385539485 cites W2950055287 @default.
• W4385539485 cites W2956328874 @default.
• W4385539485 cites W2962793481 @default.
• W4385539485 cites W2963073614 @default.
• W4385539485 cites W2963163009 @default.
• W4385539485 cites W2969134192 @default.
• W4385539485 cites W2971483169 @default.
• W4385539485 cites W2990176100 @default.
• W4385539485 cites W3001735056 @default.
• W4385539485 cites W3006777311 @default.
• W4385539485 cites W3021168584 @default.
• W4385539485 cites W3042930711 @default.
• W4385539485 cites W3044445224 @default.
• W4385539485 cites W3089519079 @default.
• W4385539485 cites W3096831136 @default.
• W4385539485 cites W3116740427 @default.
• W4385539485 cites W3125832420 @default.
• W4385539485 cites W3135038612 @default.
• W4385539485 cites W3153844346 @default.
• W4385539485 cites W3159660641 @default.
• W4385539485 cites W3175591285 @default.
• W4385539485 cites W3192774588 @default.
• W4385539485 cites W3202566931 @default.
• W4385539485 cites W4210805297 @default.
• W4385539485 cites W4220767255 @default.
• W4385539485 cites W4226213342 @default.
• W4385539485 cites W4282914989 @default.
• W4385539485 cites W4285821234 @default.
• W4385539485 cites W4286664857 @default.
• W4385539485 cites W4309197042 @default.
• W4385539485 cites W4320081372 @default.
• W4385539485 cites W4321033361 @default.
• W4385539485 cites W4362672456 @default.
• W4385539485 doi "https://doi.org/10.1016/j.engappai.2023.106743" @default.
• W4385539485 hasPublicationYear "2023" @default.
• W4385539485 type Work @default.
• W4385539485 citedByCount "1" @default.
• W4385539485 countsByYear W43855394852023 @default.
• W4385539485 crossrefType "journal-article" @default.
• W4385539485 hasAuthorship W4385539485A5014950380 @default.
• W4385539485 hasAuthorship W4385539485A5039022693 @default.
• W4385539485 hasAuthorship W4385539485A5043228449 @default.
• W4385539485 hasAuthorship W4385539485A5051197631 @default.
• W4385539485 hasAuthorship W4385539485A5086616733 @default.
• W4385539485 hasAuthorship W4385539485A5090724385 @default.
• W4385539485 hasConcept C111368507 @default.
• W4385539485 hasConcept C111919701 @default.
• W4385539485 hasConcept C118505674 @default.
• W4385539485 hasConcept C121332964 @default.
• W4385539485 hasConcept C127162648 @default.
• W4385539485 hasConcept C127313418 @default.
• W4385539485 hasConcept C138885662 @default.
• W4385539485 hasConcept C149635348 @default.
• W4385539485 hasConcept C153180895 @default.
• W4385539485 hasConcept C154945302 @default.
• W4385539485 hasConcept C163258240 @default.
• W4385539485 hasConcept C2524010 @default.
• W4385539485 hasConcept C2776401178 @default.
• W4385539485 hasConcept C2777210771 @default.
• W4385539485 hasConcept C2779803651 @default.
• W4385539485 hasConcept C2780513914 @default.
• W4385539485 hasConcept C2780992000 @default.
• W4385539485 hasConcept C31972630 @default.
• W4385539485 hasConcept C33923547 @default.
• W4385539485 hasConcept C41008148 @default.
• W4385539485 hasConcept C41895202 @default.
• W4385539485 hasConcept C62520636 @default.
• W4385539485 hasConcept C76155785 @default.
• W4385539485 hasConcept C94915269 @default.
• W4385539485 hasConcept C98083399 @default.
• W4385539485 hasConceptScore W4385539485C111368507 @default.
• W4385539485 hasConceptScore W4385539485C111919701 @default.
• W4385539485 hasConceptScore W4385539485C118505674 @default.
• W4385539485 hasConceptScore W4385539485C121332964 @default.
• W4385539485 hasConceptScore W4385539485C127162648 @default.
• W4385539485 hasConceptScore W4385539485C127313418 @default.
• W4385539485 hasConceptScore W4385539485C138885662 @default.
• W4385539485 hasConceptScore W4385539485C149635348 @default.
• W4385539485 hasConceptScore W4385539485C153180895 @default.
• W4385539485 hasConceptScore W4385539485C154945302 @default.
• W4385539485 hasConceptScore W4385539485C163258240 @default.
• W4385539485 hasConceptScore W4385539485C2524010 @default.

• next