Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387617598> ?p ?o ?g. }
- W4387617598 endingPage "8437" @default.
- W4387617598 startingPage "8437" @default.
- W4387617598 abstract "Due to the swift growth in the scale of remote sensing imagery, scholars have progressively directed their attention towards achieving efficient and adaptable cross-modal retrieval for remote sensing images. They have also steadily tackled the distinctive challenge posed by the multi-scale attributes of these images. However, existing studies primarily concentrate on the characterization of these features, neglecting the comprehensive investigation of the complex relationship between multi-scale targets and the semantic alignment of these targets with text. To address this issue, this study introduces a fine-grained semantic alignment method that adequately aggregates multi-scale information (referred to as FAAMI). The proposed approach comprises multiple stages. Initially, we employ a computing-friendly cross-layer feature connection method to construct a multi-scale feature representation of an image. Subsequently, we devise an efficient feature consistency enhancement module to rectify the incongruous semantic discrimination observed in cross-layer features. Finally, a shallow cross-attention network is employed to capture the fine-grained semantic relationship between multiple-scale image regions and the corresponding words in the text. Extensive experiments were conducted using two datasets: RSICD and RSITMD. The results demonstrate that the performance of FAAMI surpasses that of recently proposed advanced models in the same domain, with significant improvements observed in R@K and other evaluation metrics. Specifically, the mR values achieved by FAAMI are 23.18% and 35.99% for the two datasets, respectively." @default.
- W4387617598 created "2023-10-14" @default.
- W4387617598 creator A5042282225 @default.
- W4387617598 creator A5056101043 @default.
- W4387617598 creator A5061105345 @default.
- W4387617598 creator A5069050052 @default.
- W4387617598 creator A5076988030 @default.
- W4387617598 creator A5080932283 @default.
- W4387617598 creator A5086896468 @default.
- W4387617598 date "2023-10-13" @default.
- W4387617598 modified "2023-10-15" @default.
- W4387617598 title "A Fine-Grained Semantic Alignment Method Specific to Aggregate Multi-Scale Information for Cross-Modal Remote Sensing Image Retrieval" @default.
- W4387617598 cites W2107775979 @default.
- W4387617598 cites W2109255472 @default.
- W4387617598 cites W2118187752 @default.
- W4387617598 cites W2125085157 @default.
- W4387617598 cites W2151103935 @default.
- W4387617598 cites W2194775991 @default.
- W4387617598 cites W2249017129 @default.
- W4387617598 cites W2401246392 @default.
- W4387617598 cites W2412782625 @default.
- W4387617598 cites W2560023338 @default.
- W4387617598 cites W2565639579 @default.
- W4387617598 cites W2606797870 @default.
- W4387617598 cites W2768489488 @default.
- W4387617598 cites W2783363232 @default.
- W4387617598 cites W2894651257 @default.
- W4387617598 cites W2931053602 @default.
- W4387617598 cites W2962721361 @default.
- W4387617598 cites W2962964995 @default.
- W4387617598 cites W2963420686 @default.
- W4387617598 cites W2963770578 @default.
- W4387617598 cites W2963857746 @default.
- W4387617598 cites W2964120214 @default.
- W4387617598 cites W2964231884 @default.
- W4387617598 cites W2964444661 @default.
- W4387617598 cites W2988452521 @default.
- W4387617598 cites W2991488782 @default.
- W4387617598 cites W2999304331 @default.
- W4387617598 cites W3004137323 @default.
- W4387617598 cites W3034971973 @default.
- W4387617598 cites W3098774942 @default.
- W4387617598 cites W3100245404 @default.
- W4387617598 cites W3111501160 @default.
- W4387617598 cites W3116516381 @default.
- W4387617598 cites W3119231693 @default.
- W4387617598 cites W3140792177 @default.
- W4387617598 cites W3209993370 @default.
- W4387617598 cites W3212386989 @default.
- W4387617598 cites W4207037515 @default.
- W4387617598 cites W4226172762 @default.
- W4387617598 cites W4234374459 @default.
- W4387617598 cites W4281917022 @default.
- W4387617598 cites W4283029858 @default.
- W4387617598 cites W4283721482 @default.
- W4387617598 cites W4289654394 @default.
- W4387617598 cites W4292070612 @default.
- W4387617598 cites W4297505414 @default.
- W4387617598 cites W4301480362 @default.
- W4387617598 cites W4306970098 @default.
- W4387617598 cites W4309236122 @default.
- W4387617598 cites W4312219282 @default.
- W4387617598 cites W4312272363 @default.
- W4387617598 cites W4313055764 @default.
- W4387617598 cites W4313160444 @default.
- W4387617598 doi "https://doi.org/10.3390/s23208437" @default.
- W4387617598 hasPublicationYear "2023" @default.
- W4387617598 type Work @default.
- W4387617598 citedByCount "0" @default.
- W4387617598 crossrefType "journal-article" @default.
- W4387617598 hasAuthorship W4387617598A5042282225 @default.
- W4387617598 hasAuthorship W4387617598A5056101043 @default.
- W4387617598 hasAuthorship W4387617598A5061105345 @default.
- W4387617598 hasAuthorship W4387617598A5069050052 @default.
- W4387617598 hasAuthorship W4387617598A5076988030 @default.
- W4387617598 hasAuthorship W4387617598A5080932283 @default.
- W4387617598 hasAuthorship W4387617598A5086896468 @default.
- W4387617598 hasBestOaLocation W43876175981 @default.
- W4387617598 hasConcept C115961682 @default.
- W4387617598 hasConcept C124101348 @default.
- W4387617598 hasConcept C138885662 @default.
- W4387617598 hasConcept C153180895 @default.
- W4387617598 hasConcept C154945302 @default.
- W4387617598 hasConcept C159985019 @default.
- W4387617598 hasConcept C17744445 @default.
- W4387617598 hasConcept C178790620 @default.
- W4387617598 hasConcept C185592680 @default.
- W4387617598 hasConcept C188027245 @default.
- W4387617598 hasConcept C192562407 @default.
- W4387617598 hasConcept C199360897 @default.
- W4387617598 hasConcept C199539241 @default.
- W4387617598 hasConcept C205649164 @default.
- W4387617598 hasConcept C23123220 @default.
- W4387617598 hasConcept C2776359362 @default.
- W4387617598 hasConcept C2776401178 @default.
- W4387617598 hasConcept C2776436953 @default.
- W4387617598 hasConcept C2778755073 @default.
- W4387617598 hasConcept C2779227376 @default.