Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312964900> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4312964900 abstract "Current two-stage oriented object detectors for aerial images have achieved remarkable progress. However, they still suffer from some drawbacks. Firstly, most of them place redundant anchors or utilize complicated transformation to generate oriented proposals, which are inefficient. Secondly, the generation of proposals is static, which cannot adapt to the extremely nonuniform distribution of objects. To address these issues, we propose a Dynamic Proposal Generation Network (DPGN) which can generate high-quality oriented proposals directly and estimate the upper limit of proposals adaptively. To be specific, with Guided Anchor Regression (GAR), we obtain the coarse oriented anchors and utilize them to align the features. After this, we make further classification and regression to produce final oriented proposals. Meanwhile, we design Maximum Number Estimation (MNE) for predicting an approximate value to remain the proposals adaptively. Without tricks, our method can achieve competitive detection accuracy compared with other mainstream methods on DOTA dataset." @default.
- W4312964900 created "2023-01-05" @default.
- W4312964900 creator A5042202861 @default.
- W4312964900 creator A5048915407 @default.
- W4312964900 creator A5080476856 @default.
- W4312964900 creator A5087787075 @default.
- W4312964900 date "2022-07-17" @default.
- W4312964900 modified "2023-10-18" @default.
- W4312964900 title "Dynamic Proposal Generation for Oriented Object Detection in Aerial Images" @default.
- W4312964900 cites W2308318555 @default.
- W4312964900 cites W2512351403 @default.
- W4312964900 cites W2783165089 @default.
- W4312964900 cites W2855340099 @default.
- W4312964900 cites W2963299736 @default.
- W4312964900 cites W2964979676 @default.
- W4312964900 cites W2991359031 @default.
- W4312964900 cites W3022140654 @default.
- W4312964900 cites W3046174881 @default.
- W4312964900 cites W3103856189 @default.
- W4312964900 cites W3106228955 @default.
- W4312964900 cites W3201797941 @default.
- W4312964900 cites W4214648418 @default.
- W4312964900 doi "https://doi.org/10.1109/igarss46834.2022.9884707" @default.
- W4312964900 hasPublicationYear "2022" @default.
- W4312964900 type Work @default.
- W4312964900 citedByCount "1" @default.
- W4312964900 countsByYear W43129649002023 @default.
- W4312964900 crossrefType "proceedings-article" @default.
- W4312964900 hasAuthorship W4312964900A5042202861 @default.
- W4312964900 hasAuthorship W4312964900A5048915407 @default.
- W4312964900 hasAuthorship W4312964900A5080476856 @default.
- W4312964900 hasAuthorship W4312964900A5087787075 @default.
- W4312964900 hasConcept C104317684 @default.
- W4312964900 hasConcept C119857082 @default.
- W4312964900 hasConcept C124101348 @default.
- W4312964900 hasConcept C134306372 @default.
- W4312964900 hasConcept C151201525 @default.
- W4312964900 hasConcept C153180895 @default.
- W4312964900 hasConcept C154945302 @default.
- W4312964900 hasConcept C185592680 @default.
- W4312964900 hasConcept C204241405 @default.
- W4312964900 hasConcept C2776151529 @default.
- W4312964900 hasConcept C2781238097 @default.
- W4312964900 hasConcept C33923547 @default.
- W4312964900 hasConcept C41008148 @default.
- W4312964900 hasConcept C55493867 @default.
- W4312964900 hasConcept C76155785 @default.
- W4312964900 hasConcept C94915269 @default.
- W4312964900 hasConceptScore W4312964900C104317684 @default.
- W4312964900 hasConceptScore W4312964900C119857082 @default.
- W4312964900 hasConceptScore W4312964900C124101348 @default.
- W4312964900 hasConceptScore W4312964900C134306372 @default.
- W4312964900 hasConceptScore W4312964900C151201525 @default.
- W4312964900 hasConceptScore W4312964900C153180895 @default.
- W4312964900 hasConceptScore W4312964900C154945302 @default.
- W4312964900 hasConceptScore W4312964900C185592680 @default.
- W4312964900 hasConceptScore W4312964900C204241405 @default.
- W4312964900 hasConceptScore W4312964900C2776151529 @default.
- W4312964900 hasConceptScore W4312964900C2781238097 @default.
- W4312964900 hasConceptScore W4312964900C33923547 @default.
- W4312964900 hasConceptScore W4312964900C41008148 @default.
- W4312964900 hasConceptScore W4312964900C55493867 @default.
- W4312964900 hasConceptScore W4312964900C76155785 @default.
- W4312964900 hasConceptScore W4312964900C94915269 @default.
- W4312964900 hasLocation W43129649001 @default.
- W4312964900 hasOpenAccess W4312964900 @default.
- W4312964900 hasPrimaryLocation W43129649001 @default.
- W4312964900 hasRelatedWork W1971759388 @default.
- W4312964900 hasRelatedWork W2095705906 @default.
- W4312964900 hasRelatedWork W2801801420 @default.
- W4312964900 hasRelatedWork W2922421953 @default.
- W4312964900 hasRelatedWork W2970686063 @default.
- W4312964900 hasRelatedWork W2975200075 @default.
- W4312964900 hasRelatedWork W2998858795 @default.
- W4312964900 hasRelatedWork W3160733999 @default.
- W4312964900 hasRelatedWork W3187859696 @default.
- W4312964900 hasRelatedWork W4225418833 @default.
- W4312964900 isParatext "false" @default.
- W4312964900 isRetracted "false" @default.
- W4312964900 workType "article" @default.