FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895077992> ?p ?o ?g. }

• W2895077992 endingPage "761" @default.
• W2895077992 startingPage "745" @default.
• W2895077992 abstract "In this paper, we propose a graininess-aware deep feature learning method for pedestrian detection. Unlike most existing pedestrian detection methods which only consider low resolution feature maps, we incorporate fine-grained information into convolutional features to make them more discriminative for human body parts. Specifically, we propose a pedestrian attention mechanism which efficiently identifies pedestrian regions. Our method encodes fine-grained attention masks into convolutional feature maps, which significantly suppresses background interference and highlights pedestrians. Hence, our graininess-aware features become more focused on pedestrians, in particular those of small size and with occlusion. We further introduce a zoom-in-zoom-out module, which enhances the features by incorporating local details and context information. We integrate these two modules into a deep neural network, forming an end-to-end trainable pedestrian detector. Comprehensive experimental results on four challenging pedestrian benchmarks demonstrate the effectiveness of the proposed approach." @default.
• W2895077992 created "2018-10-12" @default.
• W2895077992 creator A5010357390 @default.
• W2895077992 creator A5030921116 @default.
• W2895077992 creator A5055848533 @default.
• W2895077992 creator A5090079801 @default.
• W2895077992 date "2018-01-01" @default.
• W2895077992 modified "2023-10-15" @default.
• W2895077992 title "Graininess-Aware Deep Feature Learning for Pedestrian Detection" @default.
• W2895077992 cites W1475617732 @default.
• W2895077992 cites W1536680647 @default.
• W2895077992 cites W1903029394 @default.
• W2895077992 cites W1903127635 @default.
• W2895077992 cites W1948751323 @default.
• W2895077992 cites W2034779469 @default.
• W2895077992 cites W2074777933 @default.
• W2895077992 cites W2077513643 @default.
• W2895077992 cites W2081021369 @default.
• W2895077992 cites W2084997728 @default.
• W2895077992 cites W2098064689 @default.
• W2895077992 cites W2107775979 @default.
• W2895077992 cites W2136724559 @default.
• W2895077992 cites W2140090057 @default.
• W2895077992 cites W2150066425 @default.
• W2895077992 cites W2151049637 @default.
• W2895077992 cites W2159386181 @default.
• W2895077992 cites W2162846286 @default.
• W2895077992 cites W2168356304 @default.
• W2895077992 cites W2200528286 @default.
• W2895077992 cites W2265127172 @default.
• W2895077992 cites W2474389331 @default.
• W2895077992 cites W2490270993 @default.
• W2895077992 cites W2497039038 @default.
• W2895077992 cites W2531915888 @default.
• W2895077992 cites W2534578893 @default.
• W2895077992 cites W2548197316 @default.
• W2895077992 cites W2565639579 @default.
• W2895077992 cites W2592268053 @default.
• W2895077992 cites W2613599172 @default.
• W2895077992 cites W2743905801 @default.
• W2895077992 cites W2775890136 @default.
• W2895077992 cites W2962850098 @default.
• W2895077992 cites W2963037989 @default.
• W2895077992 cites W2963998989 @default.
• W2895077992 cites W3106250896 @default.
• W2895077992 cites W3151111735 @default.
• W2895077992 doi "https://doi.org/10.1007/978-3-030-01240-3_45" @default.
• W2895077992 hasPublicationYear "2018" @default.
• W2895077992 type Work @default.
• W2895077992 sameAs 2895077992 @default.
• W2895077992 citedByCount "101" @default.
• W2895077992 countsByYear W28950779922018 @default.
• W2895077992 countsByYear W28950779922019 @default.
• W2895077992 countsByYear W28950779922020 @default.
• W2895077992 countsByYear W28950779922021 @default.
• W2895077992 countsByYear W28950779922022 @default.
• W2895077992 countsByYear W28950779922023 @default.
• W2895077992 crossrefType "book-chapter" @default.
• W2895077992 hasAuthorship W2895077992A5010357390 @default.
• W2895077992 hasAuthorship W2895077992A5030921116 @default.
• W2895077992 hasAuthorship W2895077992A5055848533 @default.
• W2895077992 hasAuthorship W2895077992A5090079801 @default.
• W2895077992 hasConcept C108583219 @default.
• W2895077992 hasConcept C124913957 @default.
• W2895077992 hasConcept C127413603 @default.
• W2895077992 hasConcept C138885662 @default.
• W2895077992 hasConcept C151730666 @default.
• W2895077992 hasConcept C153180895 @default.
• W2895077992 hasConcept C15336307 @default.
• W2895077992 hasConcept C154945302 @default.
• W2895077992 hasConcept C22212356 @default.
• W2895077992 hasConcept C2776401178 @default.
• W2895077992 hasConcept C2777113093 @default.
• W2895077992 hasConcept C2779343474 @default.
• W2895077992 hasConcept C2780156472 @default.
• W2895077992 hasConcept C31972630 @default.
• W2895077992 hasConcept C41008148 @default.
• W2895077992 hasConcept C41895202 @default.
• W2895077992 hasConcept C59404180 @default.
• W2895077992 hasConcept C78762247 @default.
• W2895077992 hasConcept C81363708 @default.
• W2895077992 hasConcept C86803240 @default.
• W2895077992 hasConcept C97931131 @default.
• W2895077992 hasConceptScore W2895077992C108583219 @default.
• W2895077992 hasConceptScore W2895077992C124913957 @default.
• W2895077992 hasConceptScore W2895077992C127413603 @default.
• W2895077992 hasConceptScore W2895077992C138885662 @default.
• W2895077992 hasConceptScore W2895077992C151730666 @default.
• W2895077992 hasConceptScore W2895077992C153180895 @default.
• W2895077992 hasConceptScore W2895077992C15336307 @default.
• W2895077992 hasConceptScore W2895077992C154945302 @default.
• W2895077992 hasConceptScore W2895077992C22212356 @default.
• W2895077992 hasConceptScore W2895077992C2776401178 @default.
• W2895077992 hasConceptScore W2895077992C2777113093 @default.
• W2895077992 hasConceptScore W2895077992C2779343474 @default.
• W2895077992 hasConceptScore W2895077992C2780156472 @default.
• W2895077992 hasConceptScore W2895077992C31972630 @default.
• W2895077992 hasConceptScore W2895077992C41008148 @default.

• next