Matches in SemOpenAlex for { <https://semopenalex.org/work/W3039701618> ?p ?o ?g. }
- W3039701618 endingPage "7000" @default.
- W3039701618 startingPage "6984" @default.
- W3039701618 abstract "Graph matching aims to establish node correspondence between two graphs, which has been a fundamental problem for its NP-hard nature. One practical consideration is the effective modeling of the affinity function in the presence of noise, such that the mathematically optimal matching result is also physically meaningful. This paper resorts to deep neural networks to learn the node and edge feature, as well as the affinity model for graph matching in an end-to-end fashion. The learning is supervised by combinatorial permutation loss over nodes. Specifically, the parameters belong to convolutional neural networks for image feature extraction, graph neural networks for node embedding that convert the structural (beyond second-order) information into node-wise features that leads to a linear assignment problem, as well as the affinity kernel between two graphs. Our approach enjoys flexibility in that the permutation loss is agnostic to the number of nodes, and the embedding model is shared among nodes such that the network can deal with varying numbers of nodes for both training and inference. Moreover, our network is class-agnostic. Experimental results on extensive benchmarks show its state-of-the-art performance. It bears some generalization capability across categories and datasets, and is capable for robust matching against outliers." @default.
- W3039701618 created "2020-07-10" @default.
- W3039701618 creator A5019708391 @default.
- W3039701618 creator A5069477050 @default.
- W3039701618 creator A5087158377 @default.
- W3039701618 date "2023-06-01" @default.
- W3039701618 modified "2023-10-04" @default.
- W3039701618 title "Combinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach" @default.
- W3039701618 cites W1556382839 @default.
- W3039701618 cites W1587878450 @default.
- W3039701618 cites W1744214816 @default.
- W3039701618 cites W1901379498 @default.
- W3039701618 cites W1990283121 @default.
- W3039701618 cites W1998840160 @default.
- W3039701618 cites W2005720384 @default.
- W3039701618 cites W2013603106 @default.
- W3039701618 cites W2031489346 @default.
- W3039701618 cites W2084512390 @default.
- W3039701618 cites W2085261163 @default.
- W3039701618 cites W2097784989 @default.
- W3039701618 cites W2108598243 @default.
- W3039701618 cites W2116341502 @default.
- W3039701618 cites W2118104180 @default.
- W3039701618 cites W2121225280 @default.
- W3039701618 cites W2126448214 @default.
- W3039701618 cites W2138910149 @default.
- W3039701618 cites W2142726150 @default.
- W3039701618 cites W2150760714 @default.
- W3039701618 cites W2152953631 @default.
- W3039701618 cites W2159537329 @default.
- W3039701618 cites W2166820607 @default.
- W3039701618 cites W2172188317 @default.
- W3039701618 cites W2189538311 @default.
- W3039701618 cites W2211710464 @default.
- W3039701618 cites W2222512263 @default.
- W3039701618 cites W2343970360 @default.
- W3039701618 cites W2369976370 @default.
- W3039701618 cites W2393319904 @default.
- W3039701618 cites W2419507445 @default.
- W3039701618 cites W2535410496 @default.
- W3039701618 cites W2765375060 @default.
- W3039701618 cites W2799132636 @default.
- W3039701618 cites W2887603607 @default.
- W3039701618 cites W2889037294 @default.
- W3039701618 cites W2895478406 @default.
- W3039701618 cites W2962756421 @default.
- W3039701618 cites W2963079738 @default.
- W3039701618 cites W2963284675 @default.
- W3039701618 cites W2963567251 @default.
- W3039701618 cites W2983178467 @default.
- W3039701618 cites W2989035356 @default.
- W3039701618 cites W2990045899 @default.
- W3039701618 cites W3104097132 @default.
- W3039701618 cites W3105705953 @default.
- W3039701618 cites W4230371388 @default.
- W3039701618 cites W48175873 @default.
- W3039701618 doi "https://doi.org/10.1109/tpami.2020.3005590" @default.
- W3039701618 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32750800" @default.
- W3039701618 hasPublicationYear "2023" @default.
- W3039701618 type Work @default.
- W3039701618 sameAs 3039701618 @default.
- W3039701618 citedByCount "28" @default.
- W3039701618 countsByYear W30397016182019 @default.
- W3039701618 countsByYear W30397016182020 @default.
- W3039701618 countsByYear W30397016182021 @default.
- W3039701618 countsByYear W30397016182022 @default.
- W3039701618 countsByYear W30397016182023 @default.
- W3039701618 crossrefType "journal-article" @default.
- W3039701618 hasAuthorship W3039701618A5019708391 @default.
- W3039701618 hasAuthorship W3039701618A5069477050 @default.
- W3039701618 hasAuthorship W3039701618A5087158377 @default.
- W3039701618 hasBestOaLocation W30397016181 @default.
- W3039701618 hasConcept C108583219 @default.
- W3039701618 hasConcept C153180895 @default.
- W3039701618 hasConcept C154945302 @default.
- W3039701618 hasConcept C41008148 @default.
- W3039701618 hasConcept C41608201 @default.
- W3039701618 hasConcept C75564084 @default.
- W3039701618 hasConcept C80444323 @default.
- W3039701618 hasConcept C81363708 @default.
- W3039701618 hasConceptScore W3039701618C108583219 @default.
- W3039701618 hasConceptScore W3039701618C153180895 @default.
- W3039701618 hasConceptScore W3039701618C154945302 @default.
- W3039701618 hasConceptScore W3039701618C41008148 @default.
- W3039701618 hasConceptScore W3039701618C41608201 @default.
- W3039701618 hasConceptScore W3039701618C75564084 @default.
- W3039701618 hasConceptScore W3039701618C80444323 @default.
- W3039701618 hasConceptScore W3039701618C81363708 @default.
- W3039701618 hasFunder F4320321001 @default.
- W3039701618 hasFunder F4320326873 @default.
- W3039701618 hasIssue "6" @default.
- W3039701618 hasLocation W30397016181 @default.
- W3039701618 hasLocation W30397016182 @default.
- W3039701618 hasOpenAccess W3039701618 @default.
- W3039701618 hasPrimaryLocation W30397016181 @default.
- W3039701618 hasRelatedWork W2731899572 @default.
- W3039701618 hasRelatedWork W2999805992 @default.
- W3039701618 hasRelatedWork W3011074480 @default.