Matches in SemOpenAlex for { <https://semopenalex.org/work/W1541601023> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W1541601023 abstract "Principal component analysis (PCA) is an unsupervised method for learning low-dimensional features with orthogonal projections. Multilinear PCA methods extend PCA to deal with multidimensional data (tensors) directly via tensor-to-tensor projection or tensor-to-vector projection (TVP). However, under the TVP setting, it is difficult to develop an effective multilinear PCA method with the orthogonality constraint. This paper tackles this problem by proposing a novel Semi-Orthogonal Multilinear PCA (SO-MPCA) approach. SO-MPCA learns low-dimensional features directly from tensors via TVP by imposing the orthogonality constraint in only one mode. This formulation results in more captured variance and more learned features than full orthogonality. For better generalization, we further introduce a relaxed start (RS) strategy to get SO-MPCA-RS by fixing the starting projection vectors, which increases the bias and reduces the variance of the learning model. Experiments on both face (2D) and gait (3D) data demonstrate that SO-MPCA-RS outperforms other competing algorithms on the whole, and the relaxed start strategy is also effective for other TVP-based PCA methods." @default.
- W1541601023 created "2016-06-24" @default.
- W1541601023 creator A5009807039 @default.
- W1541601023 creator A5038698223 @default.
- W1541601023 date "2015-04-30" @default.
- W1541601023 modified "2023-10-16" @default.
- W1541601023 title "Semi-Orthogonal Multilinear PCA with Relaxed Start" @default.
- W1541601023 cites W147615212 @default.
- W1541601023 cites W1978376511 @default.
- W1541601023 cites W2005070869 @default.
- W1541601023 cites W2018282388 @default.
- W1541601023 cites W2024165284 @default.
- W1541601023 cites W2034082601 @default.
- W1541601023 cites W2045512849 @default.
- W1541601023 cites W2055427303 @default.
- W1541601023 cites W2102544846 @default.
- W1541601023 cites W2111427896 @default.
- W1541601023 cites W2121739212 @default.
- W1541601023 cites W2138457014 @default.
- W1541601023 cites W2141200867 @default.
- W1541601023 cites W2143885292 @default.
- W1541601023 cites W2145072179 @default.
- W1541601023 cites W2146278756 @default.
- W1541601023 cites W2151458682 @default.
- W1541601023 cites W2169596663 @default.
- W1541601023 cites W2611015177 @default.
- W1541601023 cites W3099514962 @default.
- W1541601023 cites W387183918 @default.
- W1541601023 doi "https://doi.org/10.48550/arxiv.1504.08142" @default.
- W1541601023 hasPublicationYear "2015" @default.
- W1541601023 type Work @default.
- W1541601023 sameAs 1541601023 @default.
- W1541601023 citedByCount "1" @default.
- W1541601023 countsByYear W15416010232020 @default.
- W1541601023 crossrefType "posted-content" @default.
- W1541601023 hasAuthorship W1541601023A5009807039 @default.
- W1541601023 hasAuthorship W1541601023A5038698223 @default.
- W1541601023 hasBestOaLocation W15416010231 @default.
- W1541601023 hasConcept C11413529 @default.
- W1541601023 hasConcept C134306372 @default.
- W1541601023 hasConcept C153180895 @default.
- W1541601023 hasConcept C154945302 @default.
- W1541601023 hasConcept C155281189 @default.
- W1541601023 hasConcept C17137986 @default.
- W1541601023 hasConcept C175694140 @default.
- W1541601023 hasConcept C177148314 @default.
- W1541601023 hasConcept C202444582 @default.
- W1541601023 hasConcept C2524010 @default.
- W1541601023 hasConcept C27438332 @default.
- W1541601023 hasConcept C2776036281 @default.
- W1541601023 hasConcept C33923547 @default.
- W1541601023 hasConcept C41008148 @default.
- W1541601023 hasConcept C57493831 @default.
- W1541601023 hasConcept C84392682 @default.
- W1541601023 hasConceptScore W1541601023C11413529 @default.
- W1541601023 hasConceptScore W1541601023C134306372 @default.
- W1541601023 hasConceptScore W1541601023C153180895 @default.
- W1541601023 hasConceptScore W1541601023C154945302 @default.
- W1541601023 hasConceptScore W1541601023C155281189 @default.
- W1541601023 hasConceptScore W1541601023C17137986 @default.
- W1541601023 hasConceptScore W1541601023C175694140 @default.
- W1541601023 hasConceptScore W1541601023C177148314 @default.
- W1541601023 hasConceptScore W1541601023C202444582 @default.
- W1541601023 hasConceptScore W1541601023C2524010 @default.
- W1541601023 hasConceptScore W1541601023C27438332 @default.
- W1541601023 hasConceptScore W1541601023C2776036281 @default.
- W1541601023 hasConceptScore W1541601023C33923547 @default.
- W1541601023 hasConceptScore W1541601023C41008148 @default.
- W1541601023 hasConceptScore W1541601023C57493831 @default.
- W1541601023 hasConceptScore W1541601023C84392682 @default.
- W1541601023 hasLocation W15416010231 @default.
- W1541601023 hasOpenAccess W1541601023 @default.
- W1541601023 hasPrimaryLocation W15416010231 @default.
- W1541601023 hasRelatedWork W1541601023 @default.
- W1541601023 hasRelatedWork W2141200867 @default.
- W1541601023 hasRelatedWork W2143885292 @default.
- W1541601023 hasRelatedWork W2349186167 @default.
- W1541601023 hasRelatedWork W2380927352 @default.
- W1541601023 hasRelatedWork W2385772907 @default.
- W1541601023 hasRelatedWork W2537688685 @default.
- W1541601023 hasRelatedWork W2951195586 @default.
- W1541601023 hasRelatedWork W2963638086 @default.
- W1541601023 hasRelatedWork W2182871758 @default.
- W1541601023 isParatext "false" @default.
- W1541601023 isRetracted "false" @default.
- W1541601023 magId "1541601023" @default.
- W1541601023 workType "article" @default.