FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296362984> ?p ?o ?g. }

• W4296362984 endingPage "7020" @default.
• W4296362984 startingPage "7020" @default.
• W4296362984 abstract "Human action recognition and detection from unmanned aerial vehicles (UAVs), or drones, has emerged as a popular technical challenge in recent years, since it is related to many use case scenarios from environmental monitoring to search and rescue. It faces a number of difficulties mainly due to image acquisition and contents, and processing constraints. Since drones' flying conditions constrain image acquisition, human subjects may appear in images at variable scales, orientations, and occlusion, which makes action recognition more difficult. We explore low-resource methods for ML (machine learning)-based action recognition using a previously collected real-world dataset (the Okutama-Action dataset). This dataset contains representative situations for action recognition, yet is controlled for image acquisition parameters such as camera angle or flight altitude. We investigate a combination of object recognition and classifier techniques to support single-image action identification. Our architecture integrates YoloV5 with a gradient boosting classifier; the rationale is to use a scalable and efficient object recognition system coupled with a classifier that is able to incorporate samples of variable difficulty. In an ablation study, we test different architectures of YoloV5 and evaluate the performance of our method on Okutama-Action dataset. Our approach outperformed previous architectures applied to the Okutama dataset, which differed by their object identification and classification pipeline: we hypothesize that this is a consequence of both YoloV5 performance and the overall adequacy of our pipeline to the specificities of the Okutama dataset in terms of bias-variance tradeoff." @default.
• W4296362984 created "2022-09-20" @default.
• W4296362984 creator A5011693212 @default.
• W4296362984 creator A5074059447 @default.
• W4296362984 creator A5074421055 @default.
• W4296362984 creator A5076006850 @default.
• W4296362984 date "2022-09-16" @default.
• W4296362984 modified "2023-10-14" @default.
• W4296362984 title "Detecting Human Actions in Drone Images Using YoloV5 and Stochastic Gradient Boosting" @default.
• W4296362984 cites W1678356000 @default.
• W4296362984 cites W2070493638 @default.
• W4296362984 cites W2129018774 @default.
• W4296362984 cites W2149705965 @default.
• W4296362984 cites W2172207578 @default.
• W4296362984 cites W2666547004 @default.
• W4296362984 cites W2884256296 @default.
• W4296362984 cites W2901506610 @default.
• W4296362984 cites W2945676084 @default.
• W4296362984 cites W2970176295 @default.
• W4296362984 cites W2970977083 @default.
• W4296362984 cites W2990949296 @default.
• W4296362984 cites W3016641475 @default.
• W4296362984 cites W3088102655 @default.
• W4296362984 cites W3092151103 @default.
• W4296362984 cites W3102476541 @default.
• W4296362984 cites W3105022516 @default.
• W4296362984 cites W3134909472 @default.
• W4296362984 cites W3160967194 @default.
• W4296362984 cites W3173730467 @default.
• W4296362984 cites W4286212714 @default.
• W4296362984 doi "https://doi.org/10.3390/s22187020" @default.
• W4296362984 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36146369" @default.
• W4296362984 hasPublicationYear "2022" @default.
• W4296362984 type Work @default.
• W4296362984 citedByCount "13" @default.
• W4296362984 countsByYear W42963629842022 @default.
• W4296362984 countsByYear W42963629842023 @default.
• W4296362984 crossrefType "journal-article" @default.
• W4296362984 hasAuthorship W4296362984A5011693212 @default.
• W4296362984 hasAuthorship W4296362984A5074059447 @default.
• W4296362984 hasAuthorship W4296362984A5074421055 @default.
• W4296362984 hasAuthorship W4296362984A5076006850 @default.
• W4296362984 hasBestOaLocation W42963629841 @default.
• W4296362984 hasConcept C115961682 @default.
• W4296362984 hasConcept C119857082 @default.
• W4296362984 hasConcept C153180895 @default.
• W4296362984 hasConcept C154945302 @default.
• W4296362984 hasConcept C169258074 @default.
• W4296362984 hasConcept C2776151529 @default.
• W4296362984 hasConcept C2777212361 @default.
• W4296362984 hasConcept C2987834672 @default.
• W4296362984 hasConcept C31972630 @default.
• W4296362984 hasConcept C41008148 @default.
• W4296362984 hasConcept C46686674 @default.
• W4296362984 hasConcept C52622490 @default.
• W4296362984 hasConcept C54355233 @default.
• W4296362984 hasConcept C59519942 @default.
• W4296362984 hasConcept C64876066 @default.
• W4296362984 hasConcept C70153297 @default.
• W4296362984 hasConcept C75294576 @default.
• W4296362984 hasConcept C86803240 @default.
• W4296362984 hasConcept C95623464 @default.
• W4296362984 hasConceptScore W4296362984C115961682 @default.
• W4296362984 hasConceptScore W4296362984C119857082 @default.
• W4296362984 hasConceptScore W4296362984C153180895 @default.
• W4296362984 hasConceptScore W4296362984C154945302 @default.
• W4296362984 hasConceptScore W4296362984C169258074 @default.
• W4296362984 hasConceptScore W4296362984C2776151529 @default.
• W4296362984 hasConceptScore W4296362984C2777212361 @default.
• W4296362984 hasConceptScore W4296362984C2987834672 @default.
• W4296362984 hasConceptScore W4296362984C31972630 @default.
• W4296362984 hasConceptScore W4296362984C41008148 @default.
• W4296362984 hasConceptScore W4296362984C46686674 @default.
• W4296362984 hasConceptScore W4296362984C52622490 @default.
• W4296362984 hasConceptScore W4296362984C54355233 @default.
• W4296362984 hasConceptScore W4296362984C59519942 @default.
• W4296362984 hasConceptScore W4296362984C64876066 @default.
• W4296362984 hasConceptScore W4296362984C70153297 @default.
• W4296362984 hasConceptScore W4296362984C75294576 @default.
• W4296362984 hasConceptScore W4296362984C86803240 @default.
• W4296362984 hasConceptScore W4296362984C95623464 @default.
• W4296362984 hasIssue "18" @default.
• W4296362984 hasLocation W42963629841 @default.
• W4296362984 hasLocation W42963629842 @default.
• W4296362984 hasLocation W42963629843 @default.
• W4296362984 hasOpenAccess W4296362984 @default.
• W4296362984 hasPrimaryLocation W42963629841 @default.
• W4296362984 hasRelatedWork W2096112371 @default.
• W4296362984 hasRelatedWork W2955385375 @default.
• W4296362984 hasRelatedWork W3100297620 @default.
• W4296362984 hasRelatedWork W3208169454 @default.
• W4296362984 hasRelatedWork W3211193619 @default.
• W4296362984 hasRelatedWork W4212956667 @default.
• W4296362984 hasRelatedWork W4296081764 @default.
• W4296362984 hasRelatedWork W4313488044 @default.
• W4296362984 hasRelatedWork W4379536929 @default.
• W4296362984 hasRelatedWork W4382701299 @default.
• W4296362984 hasVolume "22" @default.

• next