Matches in SemOpenAlex for { <https://semopenalex.org/work/W2564853008> ?p ?o ?g. }
- W2564853008 endingPage "422" @default.
- W2564853008 startingPage "412" @default.
- W2564853008 abstract "Effective 3-D shape retrieval is an important problem in 3-D shape analysis. Recently, feature learning-based shape retrieval methods have been widely studied, where the distance metrics between 3-D shape descriptors are usually hand-crafted. In this paper, motivated by the fact that deep neural network has the good ability to model nonlinearity, we propose to learn an effective nonlinear distance metric between 3-D shape descriptors for retrieval. First, the locality-constrained linear coding method is employed to encode each vertex on the shape and the encoding coefficient histogram is formed as the global 3-D shape descriptor to represent the shape. Then, a novel deep metric network is proposed to learn a nonlinear transformation to map the 3-D shape descriptors to a nonlinear feature space. The proposed deep metric network minimizes a discriminative loss function that can enforce the similarity between a pair of samples from the same class to be small and the similarity between a pair of samples from different classes to be large. Finally, the distance between the outputs of the metric network is used as the similarity for shape retrieval. The proposed method is evaluated on the McGill, SHREC'10 ShapeGoogle, and SHREC'14 Human shape datasets. Experimental results on the three datasets validate the effectiveness of the proposed method." @default.
- W2564853008 created "2017-01-06" @default.
- W2564853008 creator A5069879969 @default.
- W2564853008 creator A5082634513 @default.
- W2564853008 creator A5089409762 @default.
- W2564853008 creator A5091721141 @default.
- W2564853008 date "2018-01-01" @default.
- W2564853008 modified "2023-09-28" @default.
- W2564853008 title "Deep Nonlinear Metric Learning for 3-D Shape Retrieval" @default.
- W2564853008 cites W1900408618 @default.
- W2564853008 cites W1964601719 @default.
- W2564853008 cites W1973122439 @default.
- W2564853008 cites W1978590356 @default.
- W2564853008 cites W1983705526 @default.
- W2564853008 cites W2007206727 @default.
- W2564853008 cites W2013442102 @default.
- W2564853008 cites W2021122545 @default.
- W2564853008 cites W2027922120 @default.
- W2564853008 cites W2034105264 @default.
- W2564853008 cites W2036163530 @default.
- W2564853008 cites W2045677161 @default.
- W2564853008 cites W2059917035 @default.
- W2564853008 cites W2071652770 @default.
- W2564853008 cites W2074781138 @default.
- W2564853008 cites W2076434944 @default.
- W2564853008 cites W2084286148 @default.
- W2564853008 cites W2088044395 @default.
- W2564853008 cites W2090967489 @default.
- W2564853008 cites W2091791686 @default.
- W2564853008 cites W2100495367 @default.
- W2564853008 cites W2100657858 @default.
- W2564853008 cites W2100740942 @default.
- W2564853008 cites W2120514892 @default.
- W2564853008 cites W2130646036 @default.
- W2564853008 cites W2137914836 @default.
- W2564853008 cites W2142873256 @default.
- W2564853008 cites W2151245724 @default.
- W2564853008 cites W2151880888 @default.
- W2564853008 cites W2152451381 @default.
- W2564853008 cites W2155957710 @default.
- W2564853008 cites W4231109964 @default.
- W2564853008 doi "https://doi.org/10.1109/tcyb.2016.2638924" @default.
- W2564853008 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28055940" @default.
- W2564853008 hasPublicationYear "2018" @default.
- W2564853008 type Work @default.
- W2564853008 sameAs 2564853008 @default.
- W2564853008 citedByCount "19" @default.
- W2564853008 countsByYear W25648530082018 @default.
- W2564853008 countsByYear W25648530082019 @default.
- W2564853008 countsByYear W25648530082020 @default.
- W2564853008 countsByYear W25648530082021 @default.
- W2564853008 countsByYear W25648530082022 @default.
- W2564853008 crossrefType "journal-article" @default.
- W2564853008 hasAuthorship W2564853008A5069879969 @default.
- W2564853008 hasAuthorship W2564853008A5082634513 @default.
- W2564853008 hasAuthorship W2564853008A5089409762 @default.
- W2564853008 hasAuthorship W2564853008A5091721141 @default.
- W2564853008 hasConcept C103278499 @default.
- W2564853008 hasConcept C104317684 @default.
- W2564853008 hasConcept C112604564 @default.
- W2564853008 hasConcept C115961682 @default.
- W2564853008 hasConcept C121332964 @default.
- W2564853008 hasConcept C129641003 @default.
- W2564853008 hasConcept C153180895 @default.
- W2564853008 hasConcept C154945302 @default.
- W2564853008 hasConcept C158622935 @default.
- W2564853008 hasConcept C162324750 @default.
- W2564853008 hasConcept C1667742 @default.
- W2564853008 hasConcept C176217482 @default.
- W2564853008 hasConcept C185592680 @default.
- W2564853008 hasConcept C199360897 @default.
- W2564853008 hasConcept C204241405 @default.
- W2564853008 hasConcept C21547014 @default.
- W2564853008 hasConcept C33923547 @default.
- W2564853008 hasConcept C41008148 @default.
- W2564853008 hasConcept C45089102 @default.
- W2564853008 hasConcept C50644808 @default.
- W2564853008 hasConcept C55493867 @default.
- W2564853008 hasConcept C62520636 @default.
- W2564853008 hasConcept C83665646 @default.
- W2564853008 hasConcept C89600930 @default.
- W2564853008 hasConcept C97686452 @default.
- W2564853008 hasConcept C97931131 @default.
- W2564853008 hasConceptScore W2564853008C103278499 @default.
- W2564853008 hasConceptScore W2564853008C104317684 @default.
- W2564853008 hasConceptScore W2564853008C112604564 @default.
- W2564853008 hasConceptScore W2564853008C115961682 @default.
- W2564853008 hasConceptScore W2564853008C121332964 @default.
- W2564853008 hasConceptScore W2564853008C129641003 @default.
- W2564853008 hasConceptScore W2564853008C153180895 @default.
- W2564853008 hasConceptScore W2564853008C154945302 @default.
- W2564853008 hasConceptScore W2564853008C158622935 @default.
- W2564853008 hasConceptScore W2564853008C162324750 @default.
- W2564853008 hasConceptScore W2564853008C1667742 @default.
- W2564853008 hasConceptScore W2564853008C176217482 @default.
- W2564853008 hasConceptScore W2564853008C185592680 @default.
- W2564853008 hasConceptScore W2564853008C199360897 @default.
- W2564853008 hasConceptScore W2564853008C204241405 @default.