Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043116150> ?p ?o ?g. }
- W3043116150 abstract "In the context of crowd counting, most of the works have focused on improving the accuracy without regard to the performance leading to algorithms that are not suitable for embedded applications. In this paper, we propose a lightweight convolutional neural network architecture to perform crowd detection and counting using fewer computer resources without a significant loss on count accuracy. The architecture was trained using the Bayes loss function to further improve its accuracy and then pruned to further reduce the computational resources used. The proposed architecture was tested over the USF-QNRF achieving a competitive Mean Average Error of 154.07 and a superior Mean Square Error of 241.77 while maintaining a competitive number of parameters of 0.067 Million. The obtained results suggest that the Bayes loss can be used with other architectures to further improve them and also the last convolutional layer provides no significant information and even encourage over-fitting at training." @default.
- W3043116150 created "2020-07-23" @default.
- W3043116150 creator A5054642793 @default.
- W3043116150 creator A5067582822 @default.
- W3043116150 date "2020-07-13" @default.
- W3043116150 modified "2023-10-01" @default.
- W3043116150 title "Dense Crowds Detection and Counting with a Lightweight Architecture." @default.
- W3043116150 cites W1677182931 @default.
- W3043116150 cites W1686810756 @default.
- W3043116150 cites W1910776219 @default.
- W3043116150 cites W1992350091 @default.
- W3043116150 cites W2122243179 @default.
- W3043116150 cites W2123175289 @default.
- W3043116150 cites W2145983039 @default.
- W3043116150 cites W2163605009 @default.
- W3043116150 cites W2463631526 @default.
- W3043116150 cites W2568510596 @default.
- W3043116150 cites W2612445135 @default.
- W3043116150 cites W2741077351 @default.
- W3043116150 cites W2886443245 @default.
- W3043116150 cites W2891915391 @default.
- W3043116150 cites W2895051362 @default.
- W3043116150 cites W2908428238 @default.
- W3043116150 cites W2918636049 @default.
- W3043116150 cites W2945574898 @default.
- W3043116150 cites W2953456714 @default.
- W3043116150 cites W2962720716 @default.
- W3043116150 cites W2962832028 @default.
- W3043116150 cites W2963163009 @default.
- W3043116150 cites W2964121744 @default.
- W3043116150 cites W2967069910 @default.
- W3043116150 cites W2970537164 @default.
- W3043116150 cites W2978859332 @default.
- W3043116150 cites W2981128131 @default.
- W3043116150 cites W2999161229 @default.
- W3043116150 cites W3004672782 @default.
- W3043116150 cites W3008125552 @default.
- W3043116150 cites W3015584482 @default.
- W3043116150 cites W3092299213 @default.
- W3043116150 cites W3095336680 @default.
- W3043116150 hasPublicationYear "2020" @default.
- W3043116150 type Work @default.
- W3043116150 sameAs 3043116150 @default.
- W3043116150 citedByCount "0" @default.
- W3043116150 crossrefType "journal-article" @default.
- W3043116150 hasAuthorship W3043116150A5054642793 @default.
- W3043116150 hasAuthorship W3043116150A5067582822 @default.
- W3043116150 hasBestOaLocation W30431161501 @default.
- W3043116150 hasConcept C105795698 @default.
- W3043116150 hasConcept C107673813 @default.
- W3043116150 hasConcept C119857082 @default.
- W3043116150 hasConcept C123657996 @default.
- W3043116150 hasConcept C139945424 @default.
- W3043116150 hasConcept C14036430 @default.
- W3043116150 hasConcept C142362112 @default.
- W3043116150 hasConcept C151730666 @default.
- W3043116150 hasConcept C153349607 @default.
- W3043116150 hasConcept C154945302 @default.
- W3043116150 hasConcept C207201462 @default.
- W3043116150 hasConcept C2777852691 @default.
- W3043116150 hasConcept C2779343474 @default.
- W3043116150 hasConcept C2944601119 @default.
- W3043116150 hasConcept C33923547 @default.
- W3043116150 hasConcept C38652104 @default.
- W3043116150 hasConcept C41008148 @default.
- W3043116150 hasConcept C78458016 @default.
- W3043116150 hasConcept C81363708 @default.
- W3043116150 hasConcept C86803240 @default.
- W3043116150 hasConceptScore W3043116150C105795698 @default.
- W3043116150 hasConceptScore W3043116150C107673813 @default.
- W3043116150 hasConceptScore W3043116150C119857082 @default.
- W3043116150 hasConceptScore W3043116150C123657996 @default.
- W3043116150 hasConceptScore W3043116150C139945424 @default.
- W3043116150 hasConceptScore W3043116150C14036430 @default.
- W3043116150 hasConceptScore W3043116150C142362112 @default.
- W3043116150 hasConceptScore W3043116150C151730666 @default.
- W3043116150 hasConceptScore W3043116150C153349607 @default.
- W3043116150 hasConceptScore W3043116150C154945302 @default.
- W3043116150 hasConceptScore W3043116150C207201462 @default.
- W3043116150 hasConceptScore W3043116150C2777852691 @default.
- W3043116150 hasConceptScore W3043116150C2779343474 @default.
- W3043116150 hasConceptScore W3043116150C2944601119 @default.
- W3043116150 hasConceptScore W3043116150C33923547 @default.
- W3043116150 hasConceptScore W3043116150C38652104 @default.
- W3043116150 hasConceptScore W3043116150C41008148 @default.
- W3043116150 hasConceptScore W3043116150C78458016 @default.
- W3043116150 hasConceptScore W3043116150C81363708 @default.
- W3043116150 hasConceptScore W3043116150C86803240 @default.
- W3043116150 hasLocation W30431161501 @default.
- W3043116150 hasOpenAccess W3043116150 @default.
- W3043116150 hasPrimaryLocation W30431161501 @default.
- W3043116150 hasRelatedWork W2737382101 @default.
- W3043116150 hasRelatedWork W2750784772 @default.
- W3043116150 hasRelatedWork W2806033632 @default.
- W3043116150 hasRelatedWork W2810573179 @default.
- W3043116150 hasRelatedWork W2963656711 @default.
- W3043116150 hasRelatedWork W2964081807 @default.
- W3043116150 hasRelatedWork W2994881943 @default.
- W3043116150 hasRelatedWork W3021814259 @default.
- W3043116150 hasRelatedWork W3034408420 @default.