Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387343896> ?p ?o ?g. }
- W4387343896 endingPage "4817" @default.
- W4387343896 startingPage "4817" @default.
- W4387343896 abstract "The quality of remote sensing images has been greatly improved by the rapid improvement of unmanned aerial vehicles (UAVs), which has made it possible to detect small objects in the most complex scenes. Recently, learning-based object detection has been introduced and has gained popularity in remote sensing image processing. To improve the detection accuracy of small, weak objects in complex scenes, this work proposes a novel hybrid backbone composed of a convolutional neural network and an adaptive multi-scaled transformer, referred to as HAM-Transformer Net. HAM-Transformer Net firstly extracts the details of feature maps using convolutional local feature extraction blocks. Secondly, hierarchical information is extracted, using multi-scale location coding. Finally, an adaptive multi-scale transformer block is used to extract further features in different receptive fields and to fuse them adaptively. We implemented comparison experiments on a self-constructed dataset. The experiments proved that the method is a significant improvement over the state-of-the-art object detection algorithms. We also conducted a large number of comparative experiments in this work to demonstrate the effectiveness of this method." @default.
- W4387343896 created "2023-10-05" @default.
- W4387343896 creator A5001315425 @default.
- W4387343896 creator A5008410383 @default.
- W4387343896 creator A5027973107 @default.
- W4387343896 creator A5045686167 @default.
- W4387343896 creator A5045742800 @default.
- W4387343896 creator A5071287264 @default.
- W4387343896 date "2023-10-03" @default.
- W4387343896 modified "2023-10-06" @default.
- W4387343896 title "HAM-Transformer: A Hybrid Adaptive Multi-Scaled Transformer Net for Remote Sensing in Complex Scenes" @default.
- W4387343896 cites W1536680647 @default.
- W4387343896 cites W2116360511 @default.
- W4387343896 cites W2194775991 @default.
- W4387343896 cites W2512351403 @default.
- W4387343896 cites W2570343428 @default.
- W4387343896 cites W2769613401 @default.
- W4387343896 cites W2962777203 @default.
- W4387343896 cites W2963037989 @default.
- W4387343896 cites W2963163009 @default.
- W4387343896 cites W2966926453 @default.
- W4387343896 cites W2982220924 @default.
- W4387343896 cites W2988916019 @default.
- W4387343896 cites W3042011474 @default.
- W4387343896 cites W3138516171 @default.
- W4387343896 cites W3175515048 @default.
- W4387343896 cites W3179888767 @default.
- W4387343896 cites W3183430956 @default.
- W4387343896 cites W3190492058 @default.
- W4387343896 cites W3201640055 @default.
- W4387343896 cites W3205100603 @default.
- W4387343896 cites W4206913762 @default.
- W4387343896 cites W4207034821 @default.
- W4387343896 cites W4223476717 @default.
- W4387343896 cites W4224132477 @default.
- W4387343896 cites W4225829036 @default.
- W4387343896 cites W4226224676 @default.
- W4387343896 cites W4288375226 @default.
- W4387343896 cites W4289545044 @default.
- W4387343896 cites W4292972665 @default.
- W4387343896 cites W4293680532 @default.
- W4387343896 cites W4309102516 @default.
- W4387343896 cites W4312443924 @default.
- W4387343896 cites W4312977443 @default.
- W4387343896 cites W4313007769 @default.
- W4387343896 cites W4313160444 @default.
- W4387343896 cites W4315865367 @default.
- W4387343896 cites W4318162656 @default.
- W4387343896 cites W4319990398 @default.
- W4387343896 cites W4320002812 @default.
- W4387343896 cites W4320009770 @default.
- W4387343896 cites W4386076325 @default.
- W4387343896 doi "https://doi.org/10.3390/rs15194817" @default.
- W4387343896 hasPublicationYear "2023" @default.
- W4387343896 type Work @default.
- W4387343896 citedByCount "0" @default.
- W4387343896 crossrefType "journal-article" @default.
- W4387343896 hasAuthorship W4387343896A5001315425 @default.
- W4387343896 hasAuthorship W4387343896A5008410383 @default.
- W4387343896 hasAuthorship W4387343896A5027973107 @default.
- W4387343896 hasAuthorship W4387343896A5045686167 @default.
- W4387343896 hasAuthorship W4387343896A5045742800 @default.
- W4387343896 hasAuthorship W4387343896A5071287264 @default.
- W4387343896 hasBestOaLocation W43873438961 @default.
- W4387343896 hasConcept C119599485 @default.
- W4387343896 hasConcept C127413603 @default.
- W4387343896 hasConcept C153180895 @default.
- W4387343896 hasConcept C154945302 @default.
- W4387343896 hasConcept C165801399 @default.
- W4387343896 hasConcept C31972630 @default.
- W4387343896 hasConcept C41008148 @default.
- W4387343896 hasConcept C52622490 @default.
- W4387343896 hasConcept C66322947 @default.
- W4387343896 hasConcept C81363708 @default.
- W4387343896 hasConceptScore W4387343896C119599485 @default.
- W4387343896 hasConceptScore W4387343896C127413603 @default.
- W4387343896 hasConceptScore W4387343896C153180895 @default.
- W4387343896 hasConceptScore W4387343896C154945302 @default.
- W4387343896 hasConceptScore W4387343896C165801399 @default.
- W4387343896 hasConceptScore W4387343896C31972630 @default.
- W4387343896 hasConceptScore W4387343896C41008148 @default.
- W4387343896 hasConceptScore W4387343896C52622490 @default.
- W4387343896 hasConceptScore W4387343896C66322947 @default.
- W4387343896 hasConceptScore W4387343896C81363708 @default.
- W4387343896 hasIssue "19" @default.
- W4387343896 hasLocation W43873438961 @default.
- W4387343896 hasOpenAccess W4387343896 @default.
- W4387343896 hasPrimaryLocation W43873438961 @default.
- W4387343896 hasRelatedWork W1964120219 @default.
- W4387343896 hasRelatedWork W2144059113 @default.
- W4387343896 hasRelatedWork W2146076056 @default.
- W4387343896 hasRelatedWork W2406522397 @default.
- W4387343896 hasRelatedWork W2767651786 @default.
- W4387343896 hasRelatedWork W2811390910 @default.
- W4387343896 hasRelatedWork W2912288872 @default.
- W4387343896 hasRelatedWork W2913302899 @default.
- W4387343896 hasRelatedWork W3003836766 @default.
- W4387343896 hasRelatedWork W4312376745 @default.