Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895588840> ?p ?o ?g. }
- W2895588840 endingPage "20" @default.
- W2895588840 startingPage "3" @default.
- W2895588840 abstract "In this paper, we present a novel deep learning framework that derives discriminative local descriptors for 3D surface shapes. In contrast to previous convolutional neural networks (CNNs) that rely on rendering multi-view images or extracting intrinsic shape properties, we parameterize the multi-scale localized neighborhoods of a keypoint into regular 2D grids, which are termed as ‘geometry images’. The benefits of such geometry images include retaining sufficient geometric information, as well as allowing the usage of standard CNNs. Specifically, we leverage a triplet network to perform deep metric learning, which takes a set of triplets as input, and a newly designed triplet loss function is minimized to distinguish between similar and dissimilar pairs of keypoints. At the testing stage, given a geometry image of a point of interest, our network outputs a discriminative local descriptor for it. Experimental results for non-rigid shape matching on several benchmarks demonstrate the superior performance of our learned descriptors over traditional descriptors and the state-of-the-art learning-based alternatives." @default.
- W2895588840 created "2018-10-12" @default.
- W2895588840 creator A5003969300 @default.
- W2895588840 creator A5016717473 @default.
- W2895588840 creator A5033354384 @default.
- W2895588840 creator A5045242540 @default.
- W2895588840 creator A5050011675 @default.
- W2895588840 date "2018-01-01" @default.
- W2895588840 modified "2023-09-30" @default.
- W2895588840 title "Learning 3D Keypoint Descriptors for Non-rigid Shape Matching" @default.
- W2895588840 cites W1558985453 @default.
- W2895588840 cites W1564871316 @default.
- W2895588840 cites W1590776313 @default.
- W2895588840 cites W1951806617 @default.
- W2895588840 cites W1975517671 @default.
- W2895588840 cites W1976584051 @default.
- W2895588840 cites W1979280606 @default.
- W2895588840 cites W1985907520 @default.
- W2895588840 cites W1989191365 @default.
- W2895588840 cites W2002552324 @default.
- W2895588840 cites W2007200979 @default.
- W2895588840 cites W2010209818 @default.
- W2895588840 cites W2013442102 @default.
- W2895588840 cites W2020682184 @default.
- W2895588840 cites W2024039087 @default.
- W2895588840 cites W2036163530 @default.
- W2895588840 cites W2059917035 @default.
- W2895588840 cites W2091791686 @default.
- W2895588840 cites W2099606917 @default.
- W2895588840 cites W2100657858 @default.
- W2895588840 cites W2122007052 @default.
- W2895588840 cites W2130646036 @default.
- W2895588840 cites W2159361280 @default.
- W2895588840 cites W2160643963 @default.
- W2895588840 cites W2173758409 @default.
- W2895588840 cites W2284800790 @default.
- W2895588840 cites W232477014 @default.
- W2895588840 cites W2398467116 @default.
- W2895588840 cites W2518780089 @default.
- W2895588840 cites W2558460151 @default.
- W2895588840 cites W2558748708 @default.
- W2895588840 cites W2566265240 @default.
- W2895588840 cites W2566657318 @default.
- W2895588840 cites W2574963313 @default.
- W2895588840 cites W2608875480 @default.
- W2895588840 cites W2783095894 @default.
- W2895588840 cites W2962865163 @default.
- W2895588840 cites W2963021451 @default.
- W2895588840 cites W2963242400 @default.
- W2895588840 cites W2963666542 @default.
- W2895588840 cites W3099206234 @default.
- W2895588840 cites W3101921002 @default.
- W2895588840 cites W4243755239 @default.
- W2895588840 doi "https://doi.org/10.1007/978-3-030-01237-3_1" @default.
- W2895588840 hasPublicationYear "2018" @default.
- W2895588840 type Work @default.
- W2895588840 sameAs 2895588840 @default.
- W2895588840 citedByCount "26" @default.
- W2895588840 countsByYear W28955888402019 @default.
- W2895588840 countsByYear W28955888402020 @default.
- W2895588840 countsByYear W28955888402021 @default.
- W2895588840 countsByYear W28955888402022 @default.
- W2895588840 countsByYear W28955888402023 @default.
- W2895588840 crossrefType "book-chapter" @default.
- W2895588840 hasAuthorship W2895588840A5003969300 @default.
- W2895588840 hasAuthorship W2895588840A5016717473 @default.
- W2895588840 hasAuthorship W2895588840A5033354384 @default.
- W2895588840 hasAuthorship W2895588840A5045242540 @default.
- W2895588840 hasAuthorship W2895588840A5050011675 @default.
- W2895588840 hasConcept C105795698 @default.
- W2895588840 hasConcept C153083717 @default.
- W2895588840 hasConcept C153180895 @default.
- W2895588840 hasConcept C154945302 @default.
- W2895588840 hasConcept C162324750 @default.
- W2895588840 hasConcept C165064840 @default.
- W2895588840 hasConcept C176217482 @default.
- W2895588840 hasConcept C205711294 @default.
- W2895588840 hasConcept C21547014 @default.
- W2895588840 hasConcept C31972630 @default.
- W2895588840 hasConcept C33923547 @default.
- W2895588840 hasConcept C41008148 @default.
- W2895588840 hasConcept C81363708 @default.
- W2895588840 hasConcept C97931131 @default.
- W2895588840 hasConceptScore W2895588840C105795698 @default.
- W2895588840 hasConceptScore W2895588840C153083717 @default.
- W2895588840 hasConceptScore W2895588840C153180895 @default.
- W2895588840 hasConceptScore W2895588840C154945302 @default.
- W2895588840 hasConceptScore W2895588840C162324750 @default.
- W2895588840 hasConceptScore W2895588840C165064840 @default.
- W2895588840 hasConceptScore W2895588840C176217482 @default.
- W2895588840 hasConceptScore W2895588840C205711294 @default.
- W2895588840 hasConceptScore W2895588840C21547014 @default.
- W2895588840 hasConceptScore W2895588840C31972630 @default.
- W2895588840 hasConceptScore W2895588840C33923547 @default.
- W2895588840 hasConceptScore W2895588840C41008148 @default.
- W2895588840 hasConceptScore W2895588840C81363708 @default.
- W2895588840 hasConceptScore W2895588840C97931131 @default.
- W2895588840 hasLocation W28955888401 @default.