FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3087907820> ?p ?o ?g. }

• W3087907820 endingPage "170897" @default.
• W3087907820 startingPage "170883" @default.
• W3087907820 abstract "Large-scale image datasets with numerous occlusion patterns prevail in real applications. The classification scheme based on subspace decomposition-based estimation with squared l <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sub> -norm regularization (SDBE_L2) has shown promising performance for the classification of partially occluded images. For the large-scale image datasets with numerous occlusion patterns, it however suffers from a high labor intensity in acquiring extra image pairs and a large consumption of computational resources in the training stage. To reduce the labor intensity, this paper enumerates several useful types of extra image pairs to guide the collection of extra images and introduces an intra-class random pairing method to semi-automatically form the extra image pairs. To alleviate the consumption of computational resources, this paper proposes two dictionary compression approaches: 1) uncentered PCA-based single partition compression (UPSPC), which compresses the dictionary to a size not larger than twice the column vector length without affecting the classification accuracy, and 2) uncentered PCA-based intra-class partition compression (UPIPC), which can further shrink the occlusion error dictionary (or class dictionary) when it has a small number of occlusion classes (or image classes). The proposed approaches are based on the property of SDBE_L2 being invariant to the uncentered PCA of sub-dictionaries. The extensive experiments on the Caltech-101 dataset and Oxford-102 flower dataset demonstrate the enumerated examples and the intra-class random pairing method facilitate acquiring the extra images and forming the extra image pairs only with a small loss in the classification accuracy. The experimental results on a large-scale occluded image dataset synthesized from the ILSVRC 2012 classification dataset with numerous occlusion patterns show that the proposed dictionary compression approaches reduce the dictionary size by over 11 times and shorten the training time by more than 39 times without loss in the classification accuracy." @default.
• W3087907820 created "2020-10-01" @default.
• W3087907820 creator A5025167286 @default.
• W3087907820 creator A5051088763 @default.
• W3087907820 creator A5052371381 @default.
• W3087907820 creator A5075853085 @default.
• W3087907820 date "2020-01-01" @default.
• W3087907820 modified "2023-09-25" @default.
• W3087907820 title "Classification of Occluded Images for Large-Scale Datasets With Numerous Occlusion Patterns" @default.
• W3087907820 cites W1963882359 @default.
• W3087907820 cites W1993241512 @default.
• W3087907820 cites W2069225252 @default.
• W3087907820 cites W2073575766 @default.
• W3087907820 cites W2094492355 @default.
• W3087907820 cites W2111605520 @default.
• W3087907820 cites W2117539524 @default.
• W3087907820 cites W2154202969 @default.
• W3087907820 cites W2166049352 @default.
• W3087907820 cites W2169991573 @default.
• W3087907820 cites W2194775991 @default.
• W3087907820 cites W2533598788 @default.
• W3087907820 cites W2557414982 @default.
• W3087907820 cites W2557449848 @default.
• W3087907820 cites W2565575913 @default.
• W3087907820 cites W2915902994 @default.
• W3087907820 cites W2956367483 @default.
• W3087907820 cites W2963420272 @default.
• W3087907820 cites W2963426391 @default.
• W3087907820 cites W2963655370 @default.
• W3087907820 cites W2964023530 @default.
• W3087907820 cites W2967079938 @default.
• W3087907820 cites W2976674591 @default.
• W3087907820 cites W2981408674 @default.
• W3087907820 cites W2997813634 @default.
• W3087907820 cites W3003244550 @default.
• W3087907820 cites W3037722013 @default.
• W3087907820 cites W3042838430 @default.
• W3087907820 cites W3043547428 @default.
• W3087907820 cites W3081436178 @default.
• W3087907820 cites W4232921201 @default.
• W3087907820 doi "https://doi.org/10.1109/access.2020.3025035" @default.
• W3087907820 hasPublicationYear "2020" @default.
• W3087907820 type Work @default.
• W3087907820 sameAs 3087907820 @default.
• W3087907820 citedByCount "1" @default.
• W3087907820 countsByYear W30879078202023 @default.
• W3087907820 crossrefType "journal-article" @default.
• W3087907820 hasAuthorship W3087907820A5025167286 @default.
• W3087907820 hasAuthorship W3087907820A5051088763 @default.
• W3087907820 hasAuthorship W3087907820A5052371381 @default.
• W3087907820 hasAuthorship W3087907820A5075853085 @default.
• W3087907820 hasBestOaLocation W30879078201 @default.
• W3087907820 hasConcept C114614502 @default.
• W3087907820 hasConcept C115961682 @default.
• W3087907820 hasConcept C153180895 @default.
• W3087907820 hasConcept C154945302 @default.
• W3087907820 hasConcept C2777212361 @default.
• W3087907820 hasConcept C33923547 @default.
• W3087907820 hasConcept C41008148 @default.
• W3087907820 hasConcept C42812 @default.
• W3087907820 hasConcept C75294576 @default.
• W3087907820 hasConceptScore W3087907820C114614502 @default.
• W3087907820 hasConceptScore W3087907820C115961682 @default.
• W3087907820 hasConceptScore W3087907820C153180895 @default.
• W3087907820 hasConceptScore W3087907820C154945302 @default.
• W3087907820 hasConceptScore W3087907820C2777212361 @default.
• W3087907820 hasConceptScore W3087907820C33923547 @default.
• W3087907820 hasConceptScore W3087907820C41008148 @default.
• W3087907820 hasConceptScore W3087907820C42812 @default.
• W3087907820 hasConceptScore W3087907820C75294576 @default.
• W3087907820 hasFunder F4320321001 @default.
• W3087907820 hasLocation W30879078201 @default.
• W3087907820 hasOpenAccess W3087907820 @default.
• W3087907820 hasPrimaryLocation W30879078201 @default.
• W3087907820 hasRelatedWork W133358225 @default.
• W3087907820 hasRelatedWork W1577137544 @default.
• W3087907820 hasRelatedWork W2041525275 @default.
• W3087907820 hasRelatedWork W2056016498 @default.
• W3087907820 hasRelatedWork W2508908072 @default.
• W3087907820 hasRelatedWork W2509146328 @default.
• W3087907820 hasRelatedWork W2537156416 @default.
• W3087907820 hasRelatedWork W2742991909 @default.
• W3087907820 hasRelatedWork W2996038082 @default.
• W3087907820 hasRelatedWork W7626849 @default.
• W3087907820 hasVolume "8" @default.
• W3087907820 isParatext "false" @default.
• W3087907820 isRetracted "false" @default.
• W3087907820 magId "3087907820" @default.
• W3087907820 workType "article" @default.