Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311176736> ?p ?o ?g. }
- W4311176736 endingPage "103727" @default.
- W4311176736 startingPage "103727" @default.
- W4311176736 abstract "Schemes to complement context relationships by cross-scale feature fusion have appeared in many RGB-D scene parsing algorithms; however, most of these works conduct multi-scale information interaction after multi-modal feature fusion, which ignores the information loss of the two modes in the original coding. Therefore, a cross-complementary fusion network (CCFNet) is designed in this paper to calibrate the multi-modal information before feature fusion, so as to improve the feature quality of each mode and the information complementarity ability of RGB and the depth map. First, we divided the features into low, middle, and high levels, among which the low-level features contain the global details of the image and the main learning features include texture, edge, and other features. The middle layer features contain not only some global detail features but also some local semantic features. Additionally, the high-level features contain rich local semantic features. Then, the feature information lost in the coding process of low and middle level features is supplemented and extracted through the designed cross feature enhancement module, and the high-level features are extracted through the feature enhancement module. In addition, the cross-modal fusion module is designed to integrate multi-modal features of different levels. The experimental results verify that the proposed CCFNet achieves excellent performance on the RGB-D scene parsing dataset containing clothing images, and the generalization ability of the model is verified by the dataset NYU Depth V2." @default.
- W4311176736 created "2022-12-24" @default.
- W4311176736 creator A5030910615 @default.
- W4311176736 creator A5056015272 @default.
- W4311176736 creator A5061528809 @default.
- W4311176736 creator A5063621364 @default.
- W4311176736 creator A5065496543 @default.
- W4311176736 creator A5076872319 @default.
- W4311176736 date "2023-02-01" @default.
- W4311176736 modified "2023-10-16" @default.
- W4311176736 title "CCFNet: Cross-Complementary fusion network for RGB-D scene parsing of clothing images" @default.
- W4311176736 cites W125693051 @default.
- W4311176736 cites W1901129140 @default.
- W4311176736 cites W1903029394 @default.
- W4311176736 cites W1955857676 @default.
- W4311176736 cites W2117539524 @default.
- W4311176736 cites W2194775991 @default.
- W4311176736 cites W2587989515 @default.
- W4311176736 cites W2595272013 @default.
- W4311176736 cites W2752782242 @default.
- W4311176736 cites W2780740184 @default.
- W4311176736 cites W2783628520 @default.
- W4311176736 cites W2799213142 @default.
- W4311176736 cites W2884585870 @default.
- W4311176736 cites W2906074946 @default.
- W4311176736 cites W2955058313 @default.
- W4311176736 cites W2963091558 @default.
- W4311176736 cites W2963727650 @default.
- W4311176736 cites W2963896186 @default.
- W4311176736 cites W2964309882 @default.
- W4311176736 cites W2971014764 @default.
- W4311176736 cites W2976113208 @default.
- W4311176736 cites W2981689412 @default.
- W4311176736 cites W2993853826 @default.
- W4311176736 cites W2997355859 @default.
- W4311176736 cites W3004257285 @default.
- W4311176736 cites W3034502973 @default.
- W4311176736 cites W3035026422 @default.
- W4311176736 cites W3035499612 @default.
- W4311176736 cites W3045052737 @default.
- W4311176736 cites W3048216881 @default.
- W4311176736 cites W3088365851 @default.
- W4311176736 cites W3097053213 @default.
- W4311176736 cites W3101839051 @default.
- W4311176736 cites W3108601100 @default.
- W4311176736 cites W3120889480 @default.
- W4311176736 cites W3127939367 @default.
- W4311176736 cites W3138111520 @default.
- W4311176736 cites W3140528754 @default.
- W4311176736 cites W3159018159 @default.
- W4311176736 cites W3163132162 @default.
- W4311176736 cites W3169283839 @default.
- W4311176736 cites W3170885821 @default.
- W4311176736 cites W3173882198 @default.
- W4311176736 cites W3198062544 @default.
- W4311176736 cites W3202169777 @default.
- W4311176736 cites W3207537403 @default.
- W4311176736 cites W3215875521 @default.
- W4311176736 cites W4200613742 @default.
- W4311176736 cites W4223571811 @default.
- W4311176736 cites W4224944713 @default.
- W4311176736 cites W4225487034 @default.
- W4311176736 cites W4226216909 @default.
- W4311176736 cites W4285205872 @default.
- W4311176736 cites W4295832202 @default.
- W4311176736 cites W4296031724 @default.
- W4311176736 cites W4304091655 @default.
- W4311176736 cites W4307297655 @default.
- W4311176736 cites W4309694881 @default.
- W4311176736 cites W4312431763 @default.
- W4311176736 cites W4313142416 @default.
- W4311176736 doi "https://doi.org/10.1016/j.jvcir.2022.103727" @default.
- W4311176736 hasPublicationYear "2023" @default.
- W4311176736 type Work @default.
- W4311176736 citedByCount "10" @default.
- W4311176736 countsByYear W43111767362022 @default.
- W4311176736 countsByYear W43111767362023 @default.
- W4311176736 crossrefType "journal-article" @default.
- W4311176736 hasAuthorship W4311176736A5030910615 @default.
- W4311176736 hasAuthorship W4311176736A5056015272 @default.
- W4311176736 hasAuthorship W4311176736A5061528809 @default.
- W4311176736 hasAuthorship W4311176736A5063621364 @default.
- W4311176736 hasAuthorship W4311176736A5065496543 @default.
- W4311176736 hasAuthorship W4311176736A5076872319 @default.
- W4311176736 hasConcept C105795698 @default.
- W4311176736 hasConcept C138885662 @default.
- W4311176736 hasConcept C151730666 @default.
- W4311176736 hasConcept C153180895 @default.
- W4311176736 hasConcept C154945302 @default.
- W4311176736 hasConcept C179518139 @default.
- W4311176736 hasConcept C186644900 @default.
- W4311176736 hasConcept C2776401178 @default.
- W4311176736 hasConcept C2779343474 @default.
- W4311176736 hasConcept C31972630 @default.
- W4311176736 hasConcept C33923547 @default.
- W4311176736 hasConcept C41008148 @default.
- W4311176736 hasConcept C41895202 @default.
- W4311176736 hasConcept C82990744 @default.