FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037850086> ?p ?o ?g. }

• W3037850086 endingPage "116899" @default.
• W3037850086 startingPage "116881" @default.
• W3037850086 abstract "Video Analytics System has emerged as a promising technology to realize deep neural network based intelligent applications for video streams. Its objective is to maximize the video analytics performance of video streams, such as accuracy, while utilizing the limited computing resource capacity efficiently. Existing video analytics systems attempt to adapt configurations to optimize resource-accuracy tradeoffs under limited resource capacity. Especially, several works recently propose a configuration adaptation algorithm based on online profiling to overcome the inefficiency of one-time offline profiling caused by the dynamics of the configuration's impact on video analytics accuracy. However, their systems are inefficient or limited to process the video analytics of multiple video streams in a GPU-enabled edge server. Furthermore, their online profiling methods still leads to a high profiling cost. In this paper, we design a video analytics system to adapt configurations for optimizing the resource-accuracy tradeoffs of multiple video streams with respect to frame rate and resolution fully under limited resource capacity of a GPU-enable edge server. In addition, we propose a lightweight online profiling method, utilizing the underlying characteristics of the video objects. Then, based on it, we propose a configuration adaptation algorithm to find the best configuration of each video stream and minimize accuracy degradation of multiple video streams under limited resource capacity of a GPU-enable edge server. To evaluate the proposed algorithm, we use a subset of surveillance videos and annotations from VIRAT 2.0 Ground dataset. The experimental results show that, in a GPU-enabled edge server, our video analytics system achieves the optimal configuration adaptation on resource-accuracy tradeoffs and our algorithm reduce the profiling cost of existing systems significantly while achieving the video analytics performance comparable to them." @default.
• W3037850086 created "2020-07-02" @default.
• W3037850086 creator A5029822491 @default.
• W3037850086 creator A5045403869 @default.
• W3037850086 date "2020-01-01" @default.
• W3037850086 modified "2023-09-24" @default.
• W3037850086 title "Lightweight Online Profiling-Based Configuration Adaptation for Video Analytics System in Edge Computing" @default.
• W3037850086 cites W2031489346 @default.
• W3037850086 cites W2105934661 @default.
• W3037850086 cites W2142996775 @default.
• W3037850086 cites W2252355370 @default.
• W3037850086 cites W2678047256 @default.
• W3037850086 cites W2752236330 @default.
• W3037850086 cites W2767650207 @default.
• W3037850086 cites W2790412025 @default.
• W3037850086 cites W2792220137 @default.
• W3037850086 cites W2801742018 @default.
• W3037850086 cites W2872933037 @default.
• W3037850086 cites W2887117815 @default.
• W3037850086 cites W2890579984 @default.
• W3037850086 cites W2896225285 @default.
• W3037850086 cites W2900140871 @default.
• W3037850086 cites W2950601690 @default.
• W3037850086 doi "https://doi.org/10.1109/access.2020.3004571" @default.
• W3037850086 hasPublicationYear "2020" @default.
• W3037850086 type Work @default.
• W3037850086 sameAs 3037850086 @default.
• W3037850086 citedByCount "14" @default.
• W3037850086 countsByYear W30378500862021 @default.
• W3037850086 countsByYear W30378500862022 @default.
• W3037850086 countsByYear W30378500862023 @default.
• W3037850086 crossrefType "journal-article" @default.
• W3037850086 hasAuthorship W3037850086A5029822491 @default.
• W3037850086 hasAuthorship W3037850086A5045403869 @default.
• W3037850086 hasBestOaLocation W30378500861 @default.
• W3037850086 hasConcept C111919701 @default.
• W3037850086 hasConcept C120314980 @default.
• W3037850086 hasConcept C124101348 @default.
• W3037850086 hasConcept C138236772 @default.
• W3037850086 hasConcept C154945302 @default.
• W3037850086 hasConcept C162307627 @default.
• W3037850086 hasConcept C187191949 @default.
• W3037850086 hasConcept C2778456923 @default.
• W3037850086 hasConcept C41008148 @default.
• W3037850086 hasConcept C79158427 @default.
• W3037850086 hasConcept C79403827 @default.
• W3037850086 hasConcept C79974875 @default.
• W3037850086 hasConceptScore W3037850086C111919701 @default.
• W3037850086 hasConceptScore W3037850086C120314980 @default.
• W3037850086 hasConceptScore W3037850086C124101348 @default.
• W3037850086 hasConceptScore W3037850086C138236772 @default.
• W3037850086 hasConceptScore W3037850086C154945302 @default.
• W3037850086 hasConceptScore W3037850086C162307627 @default.
• W3037850086 hasConceptScore W3037850086C187191949 @default.
• W3037850086 hasConceptScore W3037850086C2778456923 @default.
• W3037850086 hasConceptScore W3037850086C41008148 @default.
• W3037850086 hasConceptScore W3037850086C79158427 @default.
• W3037850086 hasConceptScore W3037850086C79403827 @default.
• W3037850086 hasConceptScore W3037850086C79974875 @default.
• W3037850086 hasLocation W30378500861 @default.
• W3037850086 hasOpenAccess W3037850086 @default.
• W3037850086 hasPrimaryLocation W30378500861 @default.
• W3037850086 hasRelatedWork W2804912624 @default.
• W3037850086 hasRelatedWork W2808334513 @default.
• W3037850086 hasRelatedWork W2896925282 @default.
• W3037850086 hasRelatedWork W2945616868 @default.
• W3037850086 hasRelatedWork W2966001425 @default.
• W3037850086 hasRelatedWork W3046945740 @default.
• W3037850086 hasRelatedWork W4200351558 @default.
• W3037850086 hasRelatedWork W4226427977 @default.
• W3037850086 hasRelatedWork W4229981831 @default.
• W3037850086 hasRelatedWork W4289389623 @default.
• W3037850086 hasVolume "8" @default.
• W3037850086 isParatext "false" @default.
• W3037850086 isRetracted "false" @default.
• W3037850086 magId "3037850086" @default.
• W3037850086 workType "article" @default.