Matches in SemOpenAlex for { <https://semopenalex.org/work/W2757996974> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2757996974 abstract "Image representation using local features and sparse coding (SC) plays a very important role in image classification when the dataset is fairly large. Despite of its worldwide popularity, there are still some improving space in classification efficiency and computational investment in training and coding phrase of SC. In this paper, we put forward a novel object categories recognition method from two aspects. First, the contextual relevance between image patches are fully utilized by merging local feature of every sub-patch with its neighboring ones into strong context features to generate the multiple sparse representations, which are received by the SC and multi-scale max pooling SPM(Spatial Pyramid Matching), respectively. Second, while calculating the sparse coefficients of SC, we need to solve L1-regularized least square problem. Screening out the zero coefficients and discarding the corresponding inactive codewords before solving Lasso problem can remarkably speed up the optimization. The proposed method outperforms state-of-the-art performance in a large number of image categorization experiments on several benchmarks: the ground truth dataset (21 Land-Use database), the event dataset (UIUC-Sport dataset), and the object recognition dataset (Caltech101 dataset)." @default.
- W2757996974 created "2017-10-06" @default.
- W2757996974 creator A5027627793 @default.
- W2757996974 creator A5070729773 @default.
- W2757996974 date "2015-12-01" @default.
- W2757996974 modified "2023-09-24" @default.
- W2757996974 title "Lasso screening for object categories recognition using multi-directional context features" @default.
- W2757996974 cites W1543911290 @default.
- W2757996974 cites W1968677218 @default.
- W2757996974 cites W2017214807 @default.
- W2757996974 cites W2027922120 @default.
- W2757996974 cites W2082025208 @default.
- W2757996974 cites W2097018403 @default.
- W2757996974 cites W2097620183 @default.
- W2757996974 cites W2107034620 @default.
- W2757996974 cites W2124386111 @default.
- W2757996974 cites W2131060185 @default.
- W2757996974 cites W2147625498 @default.
- W2757996974 cites W2151103935 @default.
- W2757996974 cites W2151259137 @default.
- W2757996974 cites W2155490028 @default.
- W2757996974 cites W2155904486 @default.
- W2757996974 cites W2162915993 @default.
- W2757996974 cites W2177274842 @default.
- W2757996974 cites W2532478580 @default.
- W2757996974 cites W3219084 @default.
- W2757996974 doi "https://doi.org/10.1109/pic.2015.7489832" @default.
- W2757996974 hasPublicationYear "2015" @default.
- W2757996974 type Work @default.
- W2757996974 sameAs 2757996974 @default.
- W2757996974 citedByCount "0" @default.
- W2757996974 crossrefType "proceedings-article" @default.
- W2757996974 hasAuthorship W2757996974A5027627793 @default.
- W2757996974 hasAuthorship W2757996974A5070729773 @default.
- W2757996974 hasConcept C115961682 @default.
- W2757996974 hasConcept C119857082 @default.
- W2757996974 hasConcept C124066611 @default.
- W2757996974 hasConcept C153180895 @default.
- W2757996974 hasConcept C154945302 @default.
- W2757996974 hasConcept C41008148 @default.
- W2757996974 hasConcept C75294576 @default.
- W2757996974 hasConcept C77637269 @default.
- W2757996974 hasConceptScore W2757996974C115961682 @default.
- W2757996974 hasConceptScore W2757996974C119857082 @default.
- W2757996974 hasConceptScore W2757996974C124066611 @default.
- W2757996974 hasConceptScore W2757996974C153180895 @default.
- W2757996974 hasConceptScore W2757996974C154945302 @default.
- W2757996974 hasConceptScore W2757996974C41008148 @default.
- W2757996974 hasConceptScore W2757996974C75294576 @default.
- W2757996974 hasConceptScore W2757996974C77637269 @default.
- W2757996974 hasLocation W27579969741 @default.
- W2757996974 hasOpenAccess W2757996974 @default.
- W2757996974 hasPrimaryLocation W27579969741 @default.
- W2757996974 hasRelatedWork W104532071 @default.
- W2757996974 hasRelatedWork W1863225007 @default.
- W2757996974 hasRelatedWork W2026188082 @default.
- W2757996974 hasRelatedWork W2036328100 @default.
- W2757996974 hasRelatedWork W2068639829 @default.
- W2757996974 hasRelatedWork W2079217005 @default.
- W2757996974 hasRelatedWork W2099580609 @default.
- W2757996974 hasRelatedWork W2161170659 @default.
- W2757996974 hasRelatedWork W2279370144 @default.
- W2757996974 hasRelatedWork W2306680624 @default.
- W2757996974 hasRelatedWork W2366450532 @default.
- W2757996974 hasRelatedWork W2396903107 @default.
- W2757996974 hasRelatedWork W2523952753 @default.
- W2757996974 hasRelatedWork W2589135627 @default.
- W2757996974 hasRelatedWork W2735663259 @default.
- W2757996974 hasRelatedWork W2898723591 @default.
- W2757996974 hasRelatedWork W2953342979 @default.
- W2757996974 hasRelatedWork W3013760272 @default.
- W2757996974 hasRelatedWork W303203082 @default.
- W2757996974 hasRelatedWork W306902760 @default.
- W2757996974 isParatext "false" @default.
- W2757996974 isRetracted "false" @default.
- W2757996974 magId "2757996974" @default.
- W2757996974 workType "article" @default.