FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2549143551> ?p ?o ?g. }

• W2549143551 abstract "Robust person detection is required by many computer vision applications. We present a deep learning approach, that combines three Convolutional Neural Networks to detect people at different scales, which is the first time that a multi-resolution model is combined with deep learning techniques in the pedestrian detection domain. The networks learn features from raw pixel information, which is also rare for pedestrian detection. Due to the use of multiple Convolutional Neural Networks at different scales, the learned features are specific for far, medium, and near scales respectively, and thus, the overall performance is improved. Furthermore, we show, that neural approaches can also be applied successfully for the remaining processing steps of classification and non-maximum suppression. The evaluation on the most popular Caltech pedestrian detection benchmark shows that the proposed method can compete with state of the art methods without using Caltech training data and without fine tuning. Therefore, it is shown that our method generalizes well on domains it is not trained on." @default.
• W2549143551 created "2016-11-30" @default.
• W2549143551 creator A5036688169 @default.
• W2549143551 creator A5066258147 @default.
• W2549143551 creator A5075114390 @default.
• W2549143551 creator A5077353311 @default.
• W2549143551 date "2016-07-01" @default.
• W2549143551 modified "2023-10-03" @default.
• W2549143551 title "Cooperative multi-scale Convolutional Neural Networks for person detection" @default.
• W2549143551 cites W10096406 @default.
• W2549143551 cites W140822990 @default.
• W2549143551 cites W1560380655 @default.
• W2549143551 cites W1602182271 @default.
• W2549143551 cites W1606347560 @default.
• W2549143551 cites W1650122911 @default.
• W2549143551 cites W1659482141 @default.
• W2549143551 cites W1904365287 @default.
• W2549143551 cites W1964483007 @default.
• W2549143551 cites W1976959044 @default.
• W2549143551 cites W1979838576 @default.
• W2549143551 cites W1986905809 @default.
• W2549143551 cites W1999853363 @default.
• W2549143551 cites W2009944334 @default.
• W2549143551 cites W2031454541 @default.
• W2549143551 cites W2032729564 @default.
• W2549143551 cites W2034779469 @default.
• W2549143551 cites W2037654606 @default.
• W2549143551 cites W2043825031 @default.
• W2549143551 cites W2047200271 @default.
• W2549143551 cites W2053842193 @default.
• W2549143551 cites W2070784585 @default.
• W2549143551 cites W2071462205 @default.
• W2549143551 cites W2077513643 @default.
• W2549143551 cites W2081021369 @default.
• W2549143551 cites W2083620785 @default.
• W2549143551 cites W2095705004 @default.
• W2549143551 cites W2104671481 @default.
• W2549143551 cites W2107775979 @default.
• W2549143551 cites W2122378993 @default.
• W2549143551 cites W2124285714 @default.
• W2549143551 cites W2125085157 @default.
• W2549143551 cites W2125556102 @default.
• W2549143551 cites W2126791727 @default.
• W2549143551 cites W2130306094 @default.
• W2549143551 cites W2133755669 @default.
• W2549143551 cites W2144506857 @default.
• W2549143551 cites W2150298366 @default.
• W2549143551 cites W2152562612 @default.
• W2549143551 cites W2156547346 @default.
• W2549143551 cites W2159386181 @default.
• W2549143551 cites W2161969291 @default.
• W2549143551 cites W2162741153 @default.
• W2549143551 cites W2168356304 @default.
• W2549143551 cites W2212677274 @default.
• W2549143551 cites W2278466186 @default.
• W2549143551 cites W2301358467 @default.
• W2549143551 cites W2537458280 @default.
• W2549143551 cites W26575457 @default.
• W2549143551 cites W39377659 @default.
• W2549143551 cites W41482161 @default.
• W2549143551 doi "https://doi.org/10.1109/ijcnn.2016.7727208" @default.
• W2549143551 hasPublicationYear "2016" @default.
• W2549143551 type Work @default.
• W2549143551 sameAs 2549143551 @default.
• W2549143551 citedByCount "14" @default.
• W2549143551 countsByYear W25491435512017 @default.
• W2549143551 countsByYear W25491435512018 @default.
• W2549143551 countsByYear W25491435512019 @default.
• W2549143551 countsByYear W25491435512020 @default.
• W2549143551 countsByYear W25491435512021 @default.
• W2549143551 crossrefType "proceedings-article" @default.
• W2549143551 hasAuthorship W2549143551A5036688169 @default.
• W2549143551 hasAuthorship W2549143551A5066258147 @default.
• W2549143551 hasAuthorship W2549143551A5075114390 @default.
• W2549143551 hasAuthorship W2549143551A5077353311 @default.
• W2549143551 hasConcept C108583219 @default.
• W2549143551 hasConcept C119857082 @default.
• W2549143551 hasConcept C127413603 @default.
• W2549143551 hasConcept C13280743 @default.
• W2549143551 hasConcept C134306372 @default.
• W2549143551 hasConcept C153180895 @default.
• W2549143551 hasConcept C154945302 @default.
• W2549143551 hasConcept C160633673 @default.
• W2549143551 hasConcept C185798385 @default.
• W2549143551 hasConcept C205649164 @default.
• W2549143551 hasConcept C22212356 @default.
• W2549143551 hasConcept C2776151529 @default.
• W2549143551 hasConcept C2777113093 @default.
• W2549143551 hasConcept C2780156472 @default.
• W2549143551 hasConcept C33923547 @default.
• W2549143551 hasConcept C36503486 @default.
• W2549143551 hasConcept C41008148 @default.
• W2549143551 hasConcept C50644808 @default.
• W2549143551 hasConcept C81363708 @default.
• W2549143551 hasConceptScore W2549143551C108583219 @default.
• W2549143551 hasConceptScore W2549143551C119857082 @default.
• W2549143551 hasConceptScore W2549143551C127413603 @default.
• W2549143551 hasConceptScore W2549143551C13280743 @default.
• W2549143551 hasConceptScore W2549143551C134306372 @default.
• W2549143551 hasConceptScore W2549143551C153180895 @default.

• next