Matches in SemOpenAlex for { <https://semopenalex.org/work/W1527369603> ?p ?o ?g. }
- W1527369603 endingPage "4714" @default.
- W1527369603 startingPage "4701" @default.
- W1527369603 abstract "Heterogeneous transfer learning has recently gained much attention as a new machine learning paradigm in which the knowledge can be transferred from source domains to target domains in different feature spaces. Existing works usually assume that source domains can provide accurate and useful knowledge to be transferred to target domains for learning. In practice, there may be noise appearing in given source (text) and target (image) domains data, and thus, the performance of transfer learning can be seriously degraded. In this paper, we propose a robust and non-negative collective matrix factorization model to handle noise in text-to-image transfer learning, and make a reliable bridge to transfer accurate and useful knowledge from the text domain to the image domain. The proposed matrix factorization model can be solved by an efficient iterative method, and the convergence of the iterative method can be shown. Extensive experiments on real data sets suggest that the proposed model is able to effectively perform transfer learning in noisy text and image domains, and it is superior to the popular existing methods for text-to-image transfer learning." @default.
- W1527369603 created "2016-06-24" @default.
- W1527369603 creator A5003431697 @default.
- W1527369603 creator A5032045741 @default.
- W1527369603 creator A5069749738 @default.
- W1527369603 date "2015-12-01" @default.
- W1527369603 modified "2023-10-15" @default.
- W1527369603 title "Robust and Non-Negative Collective Matrix Factorization for Text-to-Image Transfer Learning" @default.
- W1527369603 cites W1566135517 @default.
- W1527369603 cites W1902027874 @default.
- W1527369603 cites W1970625287 @default.
- W1527369603 cites W1986817851 @default.
- W1527369603 cites W1991207565 @default.
- W1527369603 cites W2007972815 @default.
- W1527369603 cites W2009702064 @default.
- W1527369603 cites W2023062008 @default.
- W1527369603 cites W2045405869 @default.
- W1527369603 cites W2062403535 @default.
- W1527369603 cites W2071018795 @default.
- W1527369603 cites W2076566842 @default.
- W1527369603 cites W2086820606 @default.
- W1527369603 cites W2098355853 @default.
- W1527369603 cites W2099971677 @default.
- W1527369603 cites W2107034620 @default.
- W1527369603 cites W2113154266 @default.
- W1527369603 cites W2114968688 @default.
- W1527369603 cites W2116216716 @default.
- W1527369603 cites W2117420919 @default.
- W1527369603 cites W2118375674 @default.
- W1527369603 cites W2122061064 @default.
- W1527369603 cites W2130660124 @default.
- W1527369603 cites W2132538571 @default.
- W1527369603 cites W2142674578 @default.
- W1527369603 cites W2144359569 @default.
- W1527369603 cites W2145962650 @default.
- W1527369603 cites W2151375682 @default.
- W1527369603 cites W2153635508 @default.
- W1527369603 cites W2154478709 @default.
- W1527369603 cites W2155151262 @default.
- W1527369603 cites W2162915993 @default.
- W1527369603 cites W2165698076 @default.
- W1527369603 cites W2170607218 @default.
- W1527369603 cites W2405459681 @default.
- W1527369603 cites W4205213118 @default.
- W1527369603 cites W4299439662 @default.
- W1527369603 doi "https://doi.org/10.1109/tip.2015.2465157" @default.
- W1527369603 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26259080" @default.
- W1527369603 hasPublicationYear "2015" @default.
- W1527369603 type Work @default.
- W1527369603 sameAs 1527369603 @default.
- W1527369603 citedByCount "43" @default.
- W1527369603 countsByYear W15273696032016 @default.
- W1527369603 countsByYear W15273696032017 @default.
- W1527369603 countsByYear W15273696032018 @default.
- W1527369603 countsByYear W15273696032019 @default.
- W1527369603 countsByYear W15273696032020 @default.
- W1527369603 countsByYear W15273696032021 @default.
- W1527369603 countsByYear W15273696032022 @default.
- W1527369603 countsByYear W15273696032023 @default.
- W1527369603 crossrefType "journal-article" @default.
- W1527369603 hasAuthorship W1527369603A5003431697 @default.
- W1527369603 hasAuthorship W1527369603A5032045741 @default.
- W1527369603 hasAuthorship W1527369603A5069749738 @default.
- W1527369603 hasConcept C115961682 @default.
- W1527369603 hasConcept C119857082 @default.
- W1527369603 hasConcept C121332964 @default.
- W1527369603 hasConcept C134306372 @default.
- W1527369603 hasConcept C150899416 @default.
- W1527369603 hasConcept C152671427 @default.
- W1527369603 hasConcept C153180895 @default.
- W1527369603 hasConcept C154945302 @default.
- W1527369603 hasConcept C158693339 @default.
- W1527369603 hasConcept C162324750 @default.
- W1527369603 hasConcept C2776960227 @default.
- W1527369603 hasConcept C2777303404 @default.
- W1527369603 hasConcept C33923547 @default.
- W1527369603 hasConcept C36503486 @default.
- W1527369603 hasConcept C41008148 @default.
- W1527369603 hasConcept C42355184 @default.
- W1527369603 hasConcept C50522688 @default.
- W1527369603 hasConcept C56739046 @default.
- W1527369603 hasConcept C62520636 @default.
- W1527369603 hasConcept C99498987 @default.
- W1527369603 hasConceptScore W1527369603C115961682 @default.
- W1527369603 hasConceptScore W1527369603C119857082 @default.
- W1527369603 hasConceptScore W1527369603C121332964 @default.
- W1527369603 hasConceptScore W1527369603C134306372 @default.
- W1527369603 hasConceptScore W1527369603C150899416 @default.
- W1527369603 hasConceptScore W1527369603C152671427 @default.
- W1527369603 hasConceptScore W1527369603C153180895 @default.
- W1527369603 hasConceptScore W1527369603C154945302 @default.
- W1527369603 hasConceptScore W1527369603C158693339 @default.
- W1527369603 hasConceptScore W1527369603C162324750 @default.
- W1527369603 hasConceptScore W1527369603C2776960227 @default.
- W1527369603 hasConceptScore W1527369603C2777303404 @default.
- W1527369603 hasConceptScore W1527369603C33923547 @default.
- W1527369603 hasConceptScore W1527369603C36503486 @default.
- W1527369603 hasConceptScore W1527369603C41008148 @default.