Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312804579> ?p ?o ?g. }
- W4312804579 abstract "In contrast to the generic object, aerial targets are often non-axis aligned with arbitrary orientations having the cluttered surroundings. Unlike the mainstreamed approaches regressing the bounding box orientations, this paper proposes an effective adaptive points learning approach to aerial object detection by taking advantage of the adaptive points representation, which is able to capture the geometric information of the arbitrary-oriented instances. To this end, three oriented conversion functions are presented to facilitate the classification and localization with accurate orientation. Moreover, we propose an effective quality assessment and sample assignment scheme for adaptive points learning toward choosing the representative oriented reppoints samples during training, which is able to capture the non-axis aligned features from adjacent objects or background noises. A spatial constraint is introduced to penalize the outlier points for roust adaptive learning. Experimental results on four challenging aerial datasets including DOTA, HRSC2016, UCAS-AOD and DIOR-R, demonstrate the efficacy of our proposed approach. The source code is availabel at: https://github.com/LiWentomng/OrientedRepPoints." @default.
- W4312804579 created "2023-01-05" @default.
- W4312804579 creator A5062252650 @default.
- W4312804579 creator A5067722197 @default.
- W4312804579 creator A5085295350 @default.
- W4312804579 creator A5088021291 @default.
- W4312804579 date "2022-06-01" @default.
- W4312804579 modified "2023-10-17" @default.
- W4312804579 title "Oriented RepPoints for Aerial Object Detection" @default.
- W4312804579 cites W2000358470 @default.
- W4312804579 cites W2194775991 @default.
- W4312804579 cites W2296151615 @default.
- W4312804579 cites W2560722161 @default.
- W4312804579 cites W2565639579 @default.
- W4312804579 cites W2884561390 @default.
- W4312804579 cites W2962749812 @default.
- W4312804579 cites W2962766617 @default.
- W4312804579 cites W2963037989 @default.
- W4312804579 cites W2964294787 @default.
- W4312804579 cites W2964979676 @default.
- W4312804579 cites W2970370255 @default.
- W4312804579 cites W2982770724 @default.
- W4312804579 cites W2985214930 @default.
- W4312804579 cites W2986357608 @default.
- W4312804579 cites W2989611864 @default.
- W4312804579 cites W2991359031 @default.
- W4312804579 cites W2992240579 @default.
- W4312804579 cites W2993501994 @default.
- W4312804579 cites W3012042051 @default.
- W4312804579 cites W3034993937 @default.
- W4312804579 cites W3035396860 @default.
- W4312804579 cites W3035478146 @default.
- W4312804579 cites W3092088889 @default.
- W4312804579 cites W3098218837 @default.
- W4312804579 cites W3126473426 @default.
- W4312804579 cites W3138516171 @default.
- W4312804579 cites W3167308647 @default.
- W4312804579 cites W3170033848 @default.
- W4312804579 cites W3173658130 @default.
- W4312804579 cites W3174389852 @default.
- W4312804579 cites W3174873843 @default.
- W4312804579 cites W3175496347 @default.
- W4312804579 cites W3176081225 @default.
- W4312804579 cites W3177105943 @default.
- W4312804579 cites W3201797941 @default.
- W4312804579 cites W4214648418 @default.
- W4312804579 cites W639708223 @default.
- W4312804579 doi "https://doi.org/10.1109/cvpr52688.2022.00187" @default.
- W4312804579 hasPublicationYear "2022" @default.
- W4312804579 type Work @default.
- W4312804579 citedByCount "66" @default.
- W4312804579 countsByYear W43128045792022 @default.
- W4312804579 countsByYear W43128045792023 @default.
- W4312804579 crossrefType "proceedings-article" @default.
- W4312804579 hasAuthorship W4312804579A5062252650 @default.
- W4312804579 hasAuthorship W4312804579A5067722197 @default.
- W4312804579 hasAuthorship W4312804579A5085295350 @default.
- W4312804579 hasAuthorship W4312804579A5088021291 @default.
- W4312804579 hasBestOaLocation W43128045792 @default.
- W4312804579 hasConcept C111919701 @default.
- W4312804579 hasConcept C115961682 @default.
- W4312804579 hasConcept C134306372 @default.
- W4312804579 hasConcept C147037132 @default.
- W4312804579 hasConcept C153180895 @default.
- W4312804579 hasConcept C154945302 @default.
- W4312804579 hasConcept C16345878 @default.
- W4312804579 hasConcept C177264268 @default.
- W4312804579 hasConcept C17744445 @default.
- W4312804579 hasConcept C199360897 @default.
- W4312804579 hasConcept C199539241 @default.
- W4312804579 hasConcept C2524010 @default.
- W4312804579 hasConcept C2776036281 @default.
- W4312804579 hasConcept C2776151529 @default.
- W4312804579 hasConcept C2776359362 @default.
- W4312804579 hasConcept C2776760102 @default.
- W4312804579 hasConcept C2781238097 @default.
- W4312804579 hasConcept C31972630 @default.
- W4312804579 hasConcept C33923547 @default.
- W4312804579 hasConcept C41008148 @default.
- W4312804579 hasConcept C43126263 @default.
- W4312804579 hasConcept C63584917 @default.
- W4312804579 hasConcept C77618280 @default.
- W4312804579 hasConcept C79337645 @default.
- W4312804579 hasConcept C94625758 @default.
- W4312804579 hasConceptScore W4312804579C111919701 @default.
- W4312804579 hasConceptScore W4312804579C115961682 @default.
- W4312804579 hasConceptScore W4312804579C134306372 @default.
- W4312804579 hasConceptScore W4312804579C147037132 @default.
- W4312804579 hasConceptScore W4312804579C153180895 @default.
- W4312804579 hasConceptScore W4312804579C154945302 @default.
- W4312804579 hasConceptScore W4312804579C16345878 @default.
- W4312804579 hasConceptScore W4312804579C177264268 @default.
- W4312804579 hasConceptScore W4312804579C17744445 @default.
- W4312804579 hasConceptScore W4312804579C199360897 @default.
- W4312804579 hasConceptScore W4312804579C199539241 @default.
- W4312804579 hasConceptScore W4312804579C2524010 @default.
- W4312804579 hasConceptScore W4312804579C2776036281 @default.
- W4312804579 hasConceptScore W4312804579C2776151529 @default.
- W4312804579 hasConceptScore W4312804579C2776359362 @default.
- W4312804579 hasConceptScore W4312804579C2776760102 @default.