Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321366184> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4321366184 endingPage "15" @default.
- W4321366184 startingPage "1" @default.
- W4321366184 abstract "Image matching can be transformed into the problem of feature point detection and matching of images. The current neural network methods have a weak detection effect on feature points and cannot extract enough sparse and uniform feature points. In order to improve the detection and description ability of feature points, this paper proposes a self-supervised feature point detection and description network based on asymmetric convolution: ACPoint. Specifically, first, feature point pseudolabels are learned from an unlabeled dataset, and pseudolabels are used for supervised learning; then, the learned model is used to update pseudolabels. Through multiple iterations of model training and label updating, high-quality labels and high-accuracy models are obtained adaptively. The asymmetric convolution feature point (ACPoint) network adopts an asymmetric convolution module to simultaneously train three convolution branches to learn more feature information, which uses two one-dimensional convolutions to enhance the backbone of square convolution from both horizontal and vertical directions and improve the representation of local features during inference. Based on the ACPoint network, a cross-resolution image-matching method is proposed. Experiments show that our proposed network model has higher localization accuracy and homography estimation ability on the HPatches dataset." @default.
- W4321366184 created "2023-02-21" @default.
- W4321366184 creator A5016755979 @default.
- W4321366184 creator A5024898530 @default.
- W4321366184 creator A5071146473 @default.
- W4321366184 date "2023-02-20" @default.
- W4321366184 modified "2023-10-14" @default.
- W4321366184 title "Feature Point Detection and Description Networks Based on Asymmetric Convolution and the Cross-ResolutionImage-Matching Method" @default.
- W4321366184 cites W1869500417 @default.
- W4321366184 cites W1874027545 @default.
- W4321366184 cites W1963943638 @default.
- W4321366184 cites W2090518410 @default.
- W4321366184 cites W2119605622 @default.
- W4321366184 cites W2143238378 @default.
- W4321366184 cites W2147555557 @default.
- W4321366184 cites W2149839062 @default.
- W4321366184 cites W2163009106 @default.
- W4321366184 cites W2847088336 @default.
- W4321366184 cites W2909767284 @default.
- W4321366184 cites W2964350391 @default.
- W4321366184 cites W3047057232 @default.
- W4321366184 cites W3095840465 @default.
- W4321366184 cites W3103648783 @default.
- W4321366184 cites W4226336958 @default.
- W4321366184 doi "https://doi.org/10.1155/2023/5131440" @default.
- W4321366184 hasPublicationYear "2023" @default.
- W4321366184 type Work @default.
- W4321366184 citedByCount "0" @default.
- W4321366184 crossrefType "journal-article" @default.
- W4321366184 hasAuthorship W4321366184A5016755979 @default.
- W4321366184 hasAuthorship W4321366184A5024898530 @default.
- W4321366184 hasAuthorship W4321366184A5071146473 @default.
- W4321366184 hasBestOaLocation W43213661841 @default.
- W4321366184 hasConcept C105795698 @default.
- W4321366184 hasConcept C138885662 @default.
- W4321366184 hasConcept C153180895 @default.
- W4321366184 hasConcept C154945302 @default.
- W4321366184 hasConcept C165064840 @default.
- W4321366184 hasConcept C17744445 @default.
- W4321366184 hasConcept C177846678 @default.
- W4321366184 hasConcept C199539241 @default.
- W4321366184 hasConcept C2524010 @default.
- W4321366184 hasConcept C2776214188 @default.
- W4321366184 hasConcept C2776359362 @default.
- W4321366184 hasConcept C2776401178 @default.
- W4321366184 hasConcept C28719098 @default.
- W4321366184 hasConcept C28751775 @default.
- W4321366184 hasConcept C33923547 @default.
- W4321366184 hasConcept C41008148 @default.
- W4321366184 hasConcept C41895202 @default.
- W4321366184 hasConcept C45347329 @default.
- W4321366184 hasConcept C50644808 @default.
- W4321366184 hasConcept C52622490 @default.
- W4321366184 hasConcept C75280867 @default.
- W4321366184 hasConcept C81363708 @default.
- W4321366184 hasConcept C94625758 @default.
- W4321366184 hasConceptScore W4321366184C105795698 @default.
- W4321366184 hasConceptScore W4321366184C138885662 @default.
- W4321366184 hasConceptScore W4321366184C153180895 @default.
- W4321366184 hasConceptScore W4321366184C154945302 @default.
- W4321366184 hasConceptScore W4321366184C165064840 @default.
- W4321366184 hasConceptScore W4321366184C17744445 @default.
- W4321366184 hasConceptScore W4321366184C177846678 @default.
- W4321366184 hasConceptScore W4321366184C199539241 @default.
- W4321366184 hasConceptScore W4321366184C2524010 @default.
- W4321366184 hasConceptScore W4321366184C2776214188 @default.
- W4321366184 hasConceptScore W4321366184C2776359362 @default.
- W4321366184 hasConceptScore W4321366184C2776401178 @default.
- W4321366184 hasConceptScore W4321366184C28719098 @default.
- W4321366184 hasConceptScore W4321366184C28751775 @default.
- W4321366184 hasConceptScore W4321366184C33923547 @default.
- W4321366184 hasConceptScore W4321366184C41008148 @default.
- W4321366184 hasConceptScore W4321366184C41895202 @default.
- W4321366184 hasConceptScore W4321366184C45347329 @default.
- W4321366184 hasConceptScore W4321366184C50644808 @default.
- W4321366184 hasConceptScore W4321366184C52622490 @default.
- W4321366184 hasConceptScore W4321366184C75280867 @default.
- W4321366184 hasConceptScore W4321366184C81363708 @default.
- W4321366184 hasConceptScore W4321366184C94625758 @default.
- W4321366184 hasFunder F4320321001 @default.
- W4321366184 hasLocation W43213661841 @default.
- W4321366184 hasOpenAccess W4321366184 @default.
- W4321366184 hasPrimaryLocation W43213661841 @default.
- W4321366184 hasRelatedWork W2144059113 @default.
- W4321366184 hasRelatedWork W2146076056 @default.
- W4321366184 hasRelatedWork W2295021132 @default.
- W4321366184 hasRelatedWork W2546942002 @default.
- W4321366184 hasRelatedWork W2767651786 @default.
- W4321366184 hasRelatedWork W2811390910 @default.
- W4321366184 hasRelatedWork W2913302899 @default.
- W4321366184 hasRelatedWork W4312376745 @default.
- W4321366184 hasRelatedWork W4312417841 @default.
- W4321366184 hasRelatedWork W4386303287 @default.
- W4321366184 hasVolume "2023" @default.
- W4321366184 isParatext "false" @default.
- W4321366184 isRetracted "false" @default.
- W4321366184 workType "article" @default.