Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804919> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4385804919 abstract "One of the great important fields of computer vision is semantic segmentation. As for single image semantic segmentation, due to limited available information, it appears poor performance when the occlusion and similar color interference occur, and has difficulty exploiting the rich scene information. In comparison, the special micro-len array structure of light field camera can record multi-view information of the scene, which provides us with a new solution to solve this issue. In this paper, we propose a multi-view semantic information guidance network (MSIGNet) for light field semantic segmentation. It can effectively utilize semantic information from multi-view images to guide pixel feature of center view image. First, we extract feature of each view image and further obtain semantic probability. Then all probabilities are aggregated through a self-adaptive multi-view probability fusion module. Last, the resulting coarse fusion representation interacts with center view feature to obtain the refined segmentation result. The proposed method shows excellent performance on both real-world and synthetic light field datasets." @default.
- W4385804919 created "2023-08-15" @default.
- W4385804919 creator A5013879989 @default.
- W4385804919 creator A5018365310 @default.
- W4385804919 creator A5020275874 @default.
- W4385804919 creator A5054433020 @default.
- W4385804919 creator A5064763991 @default.
- W4385804919 creator A5066353712 @default.
- W4385804919 creator A5068879407 @default.
- W4385804919 date "2023-06-01" @default.
- W4385804919 modified "2023-10-02" @default.
- W4385804919 title "Multi-view Semantic Information Guidance for Light Field Image Segmentation" @default.
- W4385804919 cites W1903029394 @default.
- W4385804919 cites W2063366997 @default.
- W4385804919 cites W2067122986 @default.
- W4385804919 cites W2146695255 @default.
- W4385804919 cites W2194775991 @default.
- W4385804919 cites W2412782625 @default.
- W4385804919 cites W2560023338 @default.
- W4385804919 cites W2798270832 @default.
- W4385804919 cites W2804860796 @default.
- W4385804919 cites W2916798096 @default.
- W4385804919 cites W2947690922 @default.
- W4385804919 cites W2954996726 @default.
- W4385804919 cites W2955058313 @default.
- W4385804919 cites W2962766617 @default.
- W4385804919 cites W2981689412 @default.
- W4385804919 cites W3035531015 @default.
- W4385804919 cites W3035807818 @default.
- W4385804919 cites W3109301572 @default.
- W4385804919 cites W3170841864 @default.
- W4385804919 cites W3194225218 @default.
- W4385804919 cites W3198139586 @default.
- W4385804919 cites W3202487219 @default.
- W4385804919 cites W3207537403 @default.
- W4385804919 cites W4214520160 @default.
- W4385804919 cites W4285134614 @default.
- W4385804919 cites W4312722796 @default.
- W4385804919 doi "https://doi.org/10.1109/cvprw59228.2023.00348" @default.
- W4385804919 hasPublicationYear "2023" @default.
- W4385804919 type Work @default.
- W4385804919 citedByCount "0" @default.
- W4385804919 crossrefType "proceedings-article" @default.
- W4385804919 hasAuthorship W4385804919A5013879989 @default.
- W4385804919 hasAuthorship W4385804919A5018365310 @default.
- W4385804919 hasAuthorship W4385804919A5020275874 @default.
- W4385804919 hasAuthorship W4385804919A5054433020 @default.
- W4385804919 hasAuthorship W4385804919A5064763991 @default.
- W4385804919 hasAuthorship W4385804919A5066353712 @default.
- W4385804919 hasAuthorship W4385804919A5068879407 @default.
- W4385804919 hasConcept C124504099 @default.
- W4385804919 hasConcept C138885662 @default.
- W4385804919 hasConcept C153180895 @default.
- W4385804919 hasConcept C154945302 @default.
- W4385804919 hasConcept C202444582 @default.
- W4385804919 hasConcept C2776401178 @default.
- W4385804919 hasConcept C31972630 @default.
- W4385804919 hasConcept C33923547 @default.
- W4385804919 hasConcept C41008148 @default.
- W4385804919 hasConcept C41895202 @default.
- W4385804919 hasConcept C89600930 @default.
- W4385804919 hasConcept C9652623 @default.
- W4385804919 hasConceptScore W4385804919C124504099 @default.
- W4385804919 hasConceptScore W4385804919C138885662 @default.
- W4385804919 hasConceptScore W4385804919C153180895 @default.
- W4385804919 hasConceptScore W4385804919C154945302 @default.
- W4385804919 hasConceptScore W4385804919C202444582 @default.
- W4385804919 hasConceptScore W4385804919C2776401178 @default.
- W4385804919 hasConceptScore W4385804919C31972630 @default.
- W4385804919 hasConceptScore W4385804919C33923547 @default.
- W4385804919 hasConceptScore W4385804919C41008148 @default.
- W4385804919 hasConceptScore W4385804919C41895202 @default.
- W4385804919 hasConceptScore W4385804919C89600930 @default.
- W4385804919 hasConceptScore W4385804919C9652623 @default.
- W4385804919 hasFunder F4320321001 @default.
- W4385804919 hasFunder F4320326978 @default.
- W4385804919 hasLocation W43858049191 @default.
- W4385804919 hasOpenAccess W4385804919 @default.
- W4385804919 hasPrimaryLocation W43858049191 @default.
- W4385804919 hasRelatedWork W1669643531 @default.
- W4385804919 hasRelatedWork W1982826852 @default.
- W4385804919 hasRelatedWork W2005437358 @default.
- W4385804919 hasRelatedWork W2008656436 @default.
- W4385804919 hasRelatedWork W2023558673 @default.
- W4385804919 hasRelatedWork W2110230079 @default.
- W4385804919 hasRelatedWork W2134924024 @default.
- W4385804919 hasRelatedWork W2517104666 @default.
- W4385804919 hasRelatedWork W2613186388 @default.
- W4385804919 hasRelatedWork W1967061043 @default.
- W4385804919 isParatext "false" @default.
- W4385804919 isRetracted "false" @default.
- W4385804919 workType "article" @default.