Matches in SemOpenAlex for { <https://semopenalex.org/work/W3191822190> ?p ?o ?g. }
- W3191822190 endingPage "109406" @default.
- W3191822190 startingPage "109396" @default.
- W3191822190 abstract "Stereo matching is an important research topic in the field of computer vision. It recovers depth information from a pair of color images. Unfortunately, converting multi-dimensional (more than two-dimensional) data into two-dimensional data, such formulations ignore the spatial structure of multi-dimensional images/data. Tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features that helps to improve the performance of the algorithm. Therefore, it is very important to establish a deep tensor model. In this paper, we propose a two layer tensor form convolutional sparse coding model, which can automatically learn the deep convolutional kernel. Based on the learned two layer convolutional kernels, a two-layer dictionary learning model is established. Then, a new weighted matching cost method is constructed, which combines shallow and deep features. The experimental results on the Middlebury benchmark v2 and Middlebury benchmark v3 show that the proposed two layer tensor convolutional sparse coding is effective for stereo matching." @default.
- W3191822190 created "2021-08-16" @default.
- W3191822190 creator A5023309071 @default.
- W3191822190 creator A5076579622 @default.
- W3191822190 date "2021-01-01" @default.
- W3191822190 modified "2023-09-25" @default.
- W3191822190 title "Two Layer Tensor Form Convolutional Sparse Coding for Stereo Matching" @default.
- W3191822190 cites W1505315132 @default.
- W3191822190 cites W1674866864 @default.
- W3191822190 cites W1912649600 @default.
- W3191822190 cites W1921093919 @default.
- W3191822190 cites W2039580825 @default.
- W3191822190 cites W2058360950 @default.
- W3191822190 cites W2061081385 @default.
- W3191822190 cites W2061113913 @default.
- W3191822190 cites W2104974755 @default.
- W3191822190 cites W2115579991 @default.
- W3191822190 cites W2148534289 @default.
- W3191822190 cites W2170921316 @default.
- W3191822190 cites W2403087908 @default.
- W3191822190 cites W2422555982 @default.
- W3191822190 cites W2440384215 @default.
- W3191822190 cites W2516455388 @default.
- W3191822190 cites W2559827556 @default.
- W3191822190 cites W2560788656 @default.
- W3191822190 cites W2592072338 @default.
- W3191822190 cites W2622664034 @default.
- W3191822190 cites W2734954306 @default.
- W3191822190 cites W2747267275 @default.
- W3191822190 cites W2762808238 @default.
- W3191822190 cites W2767899698 @default.
- W3191822190 cites W2776224886 @default.
- W3191822190 cites W2850621646 @default.
- W3191822190 cites W2897757542 @default.
- W3191822190 cites W2901527959 @default.
- W3191822190 cites W2946608878 @default.
- W3191822190 cites W2949250465 @default.
- W3191822190 cites W2963026532 @default.
- W3191822190 cites W2963316559 @default.
- W3191822190 cites W2963502507 @default.
- W3191822190 cites W2963537624 @default.
- W3191822190 cites W2963726609 @default.
- W3191822190 cites W2964002255 @default.
- W3191822190 cites W2991514044 @default.
- W3191822190 cites W3007067664 @default.
- W3191822190 cites W3022580413 @default.
- W3191822190 cites W3034308492 @default.
- W3191822190 cites W3034514115 @default.
- W3191822190 cites W3034548607 @default.
- W3191822190 cites W3045167173 @default.
- W3191822190 cites W3091750200 @default.
- W3191822190 cites W3102770796 @default.
- W3191822190 cites W3105389099 @default.
- W3191822190 cites W3119453578 @default.
- W3191822190 cites W3119502086 @default.
- W3191822190 cites W3160153841 @default.
- W3191822190 cites W55377555 @default.
- W3191822190 doi "https://doi.org/10.1109/access.2021.3102404" @default.
- W3191822190 hasPublicationYear "2021" @default.
- W3191822190 type Work @default.
- W3191822190 sameAs 3191822190 @default.
- W3191822190 citedByCount "0" @default.
- W3191822190 crossrefType "journal-article" @default.
- W3191822190 hasAuthorship W3191822190A5023309071 @default.
- W3191822190 hasAuthorship W3191822190A5076579622 @default.
- W3191822190 hasBestOaLocation W31918221901 @default.
- W3191822190 hasConcept C105795698 @default.
- W3191822190 hasConcept C108583219 @default.
- W3191822190 hasConcept C11413529 @default.
- W3191822190 hasConcept C114614502 @default.
- W3191822190 hasConcept C13280743 @default.
- W3191822190 hasConcept C153180895 @default.
- W3191822190 hasConcept C154945302 @default.
- W3191822190 hasConcept C155281189 @default.
- W3191822190 hasConcept C157899210 @default.
- W3191822190 hasConcept C165064840 @default.
- W3191822190 hasConcept C178790620 @default.
- W3191822190 hasConcept C179518139 @default.
- W3191822190 hasConcept C185592680 @default.
- W3191822190 hasConcept C185798385 @default.
- W3191822190 hasConcept C202444582 @default.
- W3191822190 hasConcept C205649164 @default.
- W3191822190 hasConcept C2779227376 @default.
- W3191822190 hasConcept C33923547 @default.
- W3191822190 hasConcept C41008148 @default.
- W3191822190 hasConcept C57273362 @default.
- W3191822190 hasConcept C74193536 @default.
- W3191822190 hasConcept C77637269 @default.
- W3191822190 hasConcept C81363708 @default.
- W3191822190 hasConceptScore W3191822190C105795698 @default.
- W3191822190 hasConceptScore W3191822190C108583219 @default.
- W3191822190 hasConceptScore W3191822190C11413529 @default.
- W3191822190 hasConceptScore W3191822190C114614502 @default.
- W3191822190 hasConceptScore W3191822190C13280743 @default.
- W3191822190 hasConceptScore W3191822190C153180895 @default.
- W3191822190 hasConceptScore W3191822190C154945302 @default.
- W3191822190 hasConceptScore W3191822190C155281189 @default.
- W3191822190 hasConceptScore W3191822190C157899210 @default.