Matches in SemOpenAlex for { <https://semopenalex.org/work/W2583665287> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2583665287 abstract "A multi-way factor analysis model is introduced for tensor-variate data of any order. Each data item is represented as a (sparse) sum of Kruskal decompositions, a Kruskal-factor analysis (KFA). KFA is nonparametric and can infer both the tensor-rank of each dictionary atom and the number of dictionary atoms. The model is adapted for online learning, which allows dictionary learning on large data sets. After KFA is introduced, the model is extended to a deep convolutional tensor-factor analysis, supervised by a Bayesian SVM. The experiments section demonstrates the improvement of KFA over vectorized approaches (e.g., BPFA), tensor decompositions, and convolutional neural networks (CNN) in multi-way denoising, blind inpainting, and image classification. The improvement in PSNR for the inpainting results over other methods exceeds 1dB in several cases and we achieve state of the art results on Caltech101 image classification." @default.
- W2583665287 created "2017-02-10" @default.
- W2583665287 creator A5001260928 @default.
- W2583665287 creator A5016448581 @default.
- W2583665287 creator A5023417820 @default.
- W2583665287 creator A5024237494 @default.
- W2583665287 creator A5072522626 @default.
- W2583665287 date "2016-12-08" @default.
- W2583665287 modified "2023-09-26" @default.
- W2583665287 title "Deep Overcomplete Tensor Rank-Decompositions." @default.
- W2583665287 cites W1428434093 @default.
- W2583665287 cites W1907282891 @default.
- W2583665287 cites W1973890885 @default.
- W2583665287 cites W2013912476 @default.
- W2583665287 cites W2024254345 @default.
- W2583665287 cites W2028795211 @default.
- W2583665287 cites W2031299022 @default.
- W2583665287 cites W2059503458 @default.
- W2583665287 cites W2086962710 @default.
- W2583665287 cites W2089007061 @default.
- W2583665287 cites W2097018403 @default.
- W2583665287 cites W2108598243 @default.
- W2583665287 cites W2112292531 @default.
- W2583665287 cites W2117111086 @default.
- W2583665287 cites W2119412403 @default.
- W2583665287 cites W2131024806 @default.
- W2583665287 cites W2140499889 @default.
- W2583665287 cites W2148461049 @default.
- W2583665287 cites W2217045154 @default.
- W2583665287 cites W233389502 @default.
- W2583665287 cites W2546302380 @default.
- W2583665287 cites W2575448204 @default.
- W2583665287 cites W3022399392 @default.
- W2583665287 hasPublicationYear "2016" @default.
- W2583665287 type Work @default.
- W2583665287 sameAs 2583665287 @default.
- W2583665287 citedByCount "0" @default.
- W2583665287 crossrefType "posted-content" @default.
- W2583665287 hasAuthorship W2583665287A5001260928 @default.
- W2583665287 hasAuthorship W2583665287A5016448581 @default.
- W2583665287 hasAuthorship W2583665287A5023417820 @default.
- W2583665287 hasAuthorship W2583665287A5024237494 @default.
- W2583665287 hasAuthorship W2583665287A5072522626 @default.
- W2583665287 hasConcept C107673813 @default.
- W2583665287 hasConcept C114614502 @default.
- W2583665287 hasConcept C115961682 @default.
- W2583665287 hasConcept C11727466 @default.
- W2583665287 hasConcept C119857082 @default.
- W2583665287 hasConcept C153180895 @default.
- W2583665287 hasConcept C154945302 @default.
- W2583665287 hasConcept C155281189 @default.
- W2583665287 hasConcept C164226766 @default.
- W2583665287 hasConcept C202444582 @default.
- W2583665287 hasConcept C33923547 @default.
- W2583665287 hasConcept C41008148 @default.
- W2583665287 hasConcept C81363708 @default.
- W2583665287 hasConceptScore W2583665287C107673813 @default.
- W2583665287 hasConceptScore W2583665287C114614502 @default.
- W2583665287 hasConceptScore W2583665287C115961682 @default.
- W2583665287 hasConceptScore W2583665287C11727466 @default.
- W2583665287 hasConceptScore W2583665287C119857082 @default.
- W2583665287 hasConceptScore W2583665287C153180895 @default.
- W2583665287 hasConceptScore W2583665287C154945302 @default.
- W2583665287 hasConceptScore W2583665287C155281189 @default.
- W2583665287 hasConceptScore W2583665287C164226766 @default.
- W2583665287 hasConceptScore W2583665287C202444582 @default.
- W2583665287 hasConceptScore W2583665287C33923547 @default.
- W2583665287 hasConceptScore W2583665287C41008148 @default.
- W2583665287 hasConceptScore W2583665287C81363708 @default.
- W2583665287 hasLocation W25836652871 @default.
- W2583665287 hasOpenAccess W2583665287 @default.
- W2583665287 hasPrimaryLocation W25836652871 @default.
- W2583665287 hasRelatedWork W1747478015 @default.
- W2583665287 hasRelatedWork W1973261891 @default.
- W2583665287 hasRelatedWork W1985529709 @default.
- W2583665287 hasRelatedWork W2063509716 @default.
- W2583665287 hasRelatedWork W2169574652 @default.
- W2583665287 hasRelatedWork W2543064516 @default.
- W2583665287 hasRelatedWork W2551959075 @default.
- W2583665287 hasRelatedWork W2763499221 @default.
- W2583665287 hasRelatedWork W2912863276 @default.
- W2583665287 hasRelatedWork W2937567175 @default.
- W2583665287 hasRelatedWork W2937824096 @default.
- W2583665287 hasRelatedWork W2949469590 @default.
- W2583665287 hasRelatedWork W2978771385 @default.
- W2583665287 hasRelatedWork W2979982309 @default.
- W2583665287 hasRelatedWork W3008566620 @default.
- W2583665287 hasRelatedWork W3015416317 @default.
- W2583665287 hasRelatedWork W3020986094 @default.
- W2583665287 hasRelatedWork W3127931969 @default.
- W2583665287 hasRelatedWork W3135385719 @default.
- W2583665287 hasRelatedWork W2962855737 @default.
- W2583665287 isParatext "false" @default.
- W2583665287 isRetracted "false" @default.
- W2583665287 magId "2583665287" @default.
- W2583665287 workType "article" @default.