Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286489553> ?p ?o ?g. }
- W4286489553 endingPage "10" @default.
- W4286489553 startingPage "1" @default.
- W4286489553 abstract "The feature information of small-scale targets is seriously missing under the interference of complex underwater terrain and light refraction. Moreover, the unbalanced distribution of underwater target samples can also affect the accuracy of spatial semantic feature extraction. Aiming at the above problems, this paper proposes a dynamic multiscale feature fusion method for underwater target recognition. Firstly, this paper uses multiscale info noise contrastive estimation (MS-InfoNCE) loss to extract the significant features of the target at 4 scales. Secondly, the method learns the spatial semantic features of the target through a dynamic conditional probability matrix. Finally, this paper designs different feature fusion mechanisms for different scale targets, dynamically fusing multiscale significant features and spatial semantic features to recognize underwater weak targets. The experimental results show that the recognition accuracy of the proposed algorithm is 1.38% higher than that of the existing algorithm when recognizing underwater distorted targets." @default.
- W4286489553 created "2022-07-22" @default.
- W4286489553 creator A5004972801 @default.
- W4286489553 creator A5007961847 @default.
- W4286489553 creator A5072365124 @default.
- W4286489553 creator A5081396646 @default.
- W4286489553 date "2022-07-21" @default.
- W4286489553 modified "2023-10-17" @default.
- W4286489553 title "Dynamic Multiscale Feature Fusion Method for Underwater Target Recognition" @default.
- W4286489553 cites W2604795365 @default.
- W4286489553 cites W2626919280 @default.
- W4286489553 cites W2793523928 @default.
- W4286489553 cites W2914383137 @default.
- W4286489553 cites W2929000277 @default.
- W4286489553 cites W2963322224 @default.
- W4286489553 cites W2969218386 @default.
- W4286489553 cites W3003281790 @default.
- W4286489553 cites W3007833995 @default.
- W4286489553 cites W3009977275 @default.
- W4286489553 cites W3027585699 @default.
- W4286489553 cites W3036328963 @default.
- W4286489553 cites W3040977527 @default.
- W4286489553 cites W3046828085 @default.
- W4286489553 cites W3046887343 @default.
- W4286489553 cites W3048553410 @default.
- W4286489553 cites W3080642275 @default.
- W4286489553 cites W3091593115 @default.
- W4286489553 cites W3107034740 @default.
- W4286489553 cites W3108328895 @default.
- W4286489553 cites W3109067582 @default.
- W4286489553 cites W3125723491 @default.
- W4286489553 cites W3154613065 @default.
- W4286489553 cites W3205347094 @default.
- W4286489553 cites W3207903433 @default.
- W4286489553 cites W4206294875 @default.
- W4286489553 doi "https://doi.org/10.1155/2022/8110695" @default.
- W4286489553 hasPublicationYear "2022" @default.
- W4286489553 type Work @default.
- W4286489553 citedByCount "2" @default.
- W4286489553 countsByYear W42864895532023 @default.
- W4286489553 crossrefType "journal-article" @default.
- W4286489553 hasAuthorship W4286489553A5004972801 @default.
- W4286489553 hasAuthorship W4286489553A5007961847 @default.
- W4286489553 hasAuthorship W4286489553A5072365124 @default.
- W4286489553 hasAuthorship W4286489553A5081396646 @default.
- W4286489553 hasBestOaLocation W42864895531 @default.
- W4286489553 hasConcept C115961682 @default.
- W4286489553 hasConcept C127162648 @default.
- W4286489553 hasConcept C138885662 @default.
- W4286489553 hasConcept C153180895 @default.
- W4286489553 hasConcept C154945302 @default.
- W4286489553 hasConcept C158525013 @default.
- W4286489553 hasConcept C161840515 @default.
- W4286489553 hasConcept C166957645 @default.
- W4286489553 hasConcept C205649164 @default.
- W4286489553 hasConcept C2776401178 @default.
- W4286489553 hasConcept C31258907 @default.
- W4286489553 hasConcept C31972630 @default.
- W4286489553 hasConcept C32022120 @default.
- W4286489553 hasConcept C41008148 @default.
- W4286489553 hasConcept C41895202 @default.
- W4286489553 hasConcept C52622490 @default.
- W4286489553 hasConcept C58640448 @default.
- W4286489553 hasConcept C98083399 @default.
- W4286489553 hasConcept C99498987 @default.
- W4286489553 hasConceptScore W4286489553C115961682 @default.
- W4286489553 hasConceptScore W4286489553C127162648 @default.
- W4286489553 hasConceptScore W4286489553C138885662 @default.
- W4286489553 hasConceptScore W4286489553C153180895 @default.
- W4286489553 hasConceptScore W4286489553C154945302 @default.
- W4286489553 hasConceptScore W4286489553C158525013 @default.
- W4286489553 hasConceptScore W4286489553C161840515 @default.
- W4286489553 hasConceptScore W4286489553C166957645 @default.
- W4286489553 hasConceptScore W4286489553C205649164 @default.
- W4286489553 hasConceptScore W4286489553C2776401178 @default.
- W4286489553 hasConceptScore W4286489553C31258907 @default.
- W4286489553 hasConceptScore W4286489553C31972630 @default.
- W4286489553 hasConceptScore W4286489553C32022120 @default.
- W4286489553 hasConceptScore W4286489553C41008148 @default.
- W4286489553 hasConceptScore W4286489553C41895202 @default.
- W4286489553 hasConceptScore W4286489553C52622490 @default.
- W4286489553 hasConceptScore W4286489553C58640448 @default.
- W4286489553 hasConceptScore W4286489553C98083399 @default.
- W4286489553 hasConceptScore W4286489553C99498987 @default.
- W4286489553 hasFunder F4320335777 @default.
- W4286489553 hasLocation W42864895531 @default.
- W4286489553 hasLocation W42864895532 @default.
- W4286489553 hasOpenAccess W4286489553 @default.
- W4286489553 hasPrimaryLocation W42864895531 @default.
- W4286489553 hasRelatedWork W1504288058 @default.
- W4286489553 hasRelatedWork W2048505601 @default.
- W4286489553 hasRelatedWork W2146076056 @default.
- W4286489553 hasRelatedWork W2167293474 @default.
- W4286489553 hasRelatedWork W2170917786 @default.
- W4286489553 hasRelatedWork W2331674254 @default.
- W4286489553 hasRelatedWork W2546942002 @default.
- W4286489553 hasRelatedWork W2742702720 @default.
- W4286489553 hasRelatedWork W2811390910 @default.