FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285216854> ?p ?o ?g. }

• W4285216854 endingPage "53809" @default.
• W4285216854 startingPage "53797" @default.
• W4285216854 abstract "Multispectral pedestrian detection based on deep learning can provide a robust and accurate detection under different illumination conditions, which has important research significance in safety. In order to reduce the log-average miss rate of the object under different illumination conditions, a new one-stage detector suitable for multispectral pedestrian detection is proposed. First, in order to realize the complementarity between the information flows of the two modalities in the feature extraction stage to reduce the object loss, a low-cost cross-modality feature complementary module (CFCM) is proposed. Second, in order to suppress the background noise in different environments and enhance the semantic information and location information of the object, so as to reduce the error detection of the object, an attention-based feature enhancement fusion module (AFEFM) is proposed. Thirdly, through the feature complementarity of color-thermal image pair and the multi-scale fusion of depth feature layer, the horizontal and vertical multi-dimensional data mining of parallel deep neural network is realized, which provides effective data support for object detection algorithm. Finally, through the reasonable arrangement of proposed modules, a robust multispectral detection framework is proposed. The experimental results on the Korea Advanced Institute of Science and Technology (KAIST) pedestrian benchmark show that the proposed method has the lowest log-average miss rate compared with other state-of-the-art multispectral pedestrian detectors, and has a good balance in speed and accuracy." @default.
• W4285216854 created "2022-07-14" @default.
• W4285216854 creator A5019643940 @default.
• W4285216854 creator A5027786646 @default.
• W4285216854 creator A5029494148 @default.
• W4285216854 creator A5056491821 @default.
• W4285216854 creator A5062515720 @default.
• W4285216854 creator A5066402253 @default.
• W4285216854 date "2022-01-01" @default.
• W4285216854 modified "2023-10-14" @default.
• W4285216854 title "Attention-Based Cross-Modality Feature Complementation for Multispectral Pedestrian Detection" @default.
• W4285216854 cites W1526734559 @default.
• W4285216854 cites W1910108985 @default.
• W4285216854 cites W2031454541 @default.
• W4285216854 cites W2039051707 @default.
• W4285216854 cites W2121955477 @default.
• W4285216854 cites W2123533187 @default.
• W4285216854 cites W2161969291 @default.
• W4285216854 cites W2428342532 @default.
• W4285216854 cites W2539122319 @default.
• W4285216854 cites W2752263152 @default.
• W4285216854 cites W2807577763 @default.
• W4285216854 cites W2883279456 @default.
• W4285216854 cites W2955573317 @default.
• W4285216854 cites W2963188557 @default.
• W4285216854 cites W2963315052 @default.
• W4285216854 cites W2963318220 @default.
• W4285216854 cites W2963404857 @default.
• W4285216854 cites W2963579094 @default.
• W4285216854 cites W2964027659 @default.
• W4285216854 cites W2987131085 @default.
• W4285216854 cites W3009882457 @default.
• W4285216854 cites W3026181888 @default.
• W4285216854 cites W3032319694 @default.
• W4285216854 cites W3034696777 @default.
• W4285216854 cites W3035323039 @default.
• W4285216854 cites W3036931590 @default.
• W4285216854 cites W3047853272 @default.
• W4285216854 cites W3084389333 @default.
• W4285216854 cites W3097905314 @default.
• W4285216854 cites W3099239430 @default.
• W4285216854 cites W3104978563 @default.
• W4285216854 cites W3111157437 @default.
• W4285216854 cites W3118570274 @default.
• W4285216854 cites W3119785658 @default.
• W4285216854 cites W3129282701 @default.
• W4285216854 cites W3130004281 @default.
• W4285216854 cites W3135982978 @default.
• W4285216854 cites W3152390103 @default.
• W4285216854 cites W3160361512 @default.
• W4285216854 cites W3163653668 @default.
• W4285216854 cites W3164576087 @default.
• W4285216854 cites W3173018607 @default.
• W4285216854 cites W3173632533 @default.
• W4285216854 cites W3174058041 @default.
• W4285216854 cites W3176159061 @default.
• W4285216854 cites W3177052299 @default.
• W4285216854 cites W3180134609 @default.
• W4285216854 cites W3189456603 @default.
• W4285216854 cites W3193933482 @default.
• W4285216854 cites W3203755984 @default.
• W4285216854 cites W639708223 @default.
• W4285216854 doi "https://doi.org/10.1109/access.2022.3175303" @default.
• W4285216854 hasPublicationYear "2022" @default.
• W4285216854 type Work @default.
• W4285216854 citedByCount "4" @default.
• W4285216854 countsByYear W42852168542022 @default.
• W4285216854 countsByYear W42852168542023 @default.
• W4285216854 crossrefType "journal-article" @default.
• W4285216854 hasAuthorship W4285216854A5019643940 @default.
• W4285216854 hasAuthorship W4285216854A5027786646 @default.
• W4285216854 hasAuthorship W4285216854A5029494148 @default.
• W4285216854 hasAuthorship W4285216854A5056491821 @default.
• W4285216854 hasAuthorship W4285216854A5062515720 @default.
• W4285216854 hasAuthorship W4285216854A5066402253 @default.
• W4285216854 hasBestOaLocation W42852168541 @default.
• W4285216854 hasConcept C127413603 @default.
• W4285216854 hasConcept C138885662 @default.
• W4285216854 hasConcept C153180895 @default.
• W4285216854 hasConcept C154945302 @default.
• W4285216854 hasConcept C173163844 @default.
• W4285216854 hasConcept C22212356 @default.
• W4285216854 hasConcept C2776151529 @default.
• W4285216854 hasConcept C2776401178 @default.
• W4285216854 hasConcept C2777113093 @default.
• W4285216854 hasConcept C2780156472 @default.
• W4285216854 hasConcept C31972630 @default.
• W4285216854 hasConcept C41008148 @default.
• W4285216854 hasConcept C41895202 @default.
• W4285216854 hasConcept C52622490 @default.
• W4285216854 hasConcept C76155785 @default.
• W4285216854 hasConcept C81363708 @default.
• W4285216854 hasConcept C94915269 @default.
• W4285216854 hasConceptScore W4285216854C127413603 @default.
• W4285216854 hasConceptScore W4285216854C138885662 @default.
• W4285216854 hasConceptScore W4285216854C153180895 @default.
• W4285216854 hasConceptScore W4285216854C154945302 @default.
• W4285216854 hasConceptScore W4285216854C173163844 @default.

• next