FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899272034> ?p ?o ?g. }

• W2899272034 endingPage "7416" @default.
• W2899272034 startingPage "7407" @default.
• W2899272034 abstract "The scene text interpretation is a critical part of the natural scene interpretation. Currently, most of the existing work is based on high-end graphics processing units (GPUs) implementation, which is commonly used on the server side. However, in Internet of Things (IoT) application scenarios, the communication overhead from the edge device to the server is quite large, which sometimes even dominates the total processing time. Hence, the edge-computing oriented design is needed to solve this problem. In this paper, we present an architectural design and implementation of a natural scene text interpretation (NSTI) accelerator, which can classify and localize the text region on pixel-level efficiently in real-time on mobile devices. To target the real-time and low-latency processing, the binary convolutional encoder-decoder network is adopted as the core architecture to enable massive parallelism due to its binary feature. Massively parallelized computations and a highly pipelined data flow control enhance its latency and throughput performance. In addition, all the binarized intermediate results and parameters are stored on chip to eliminate the power consumption and latency overhead of the off-chip communication. The NSTI accelerator is implemented in a 40 nm CMOS technology, which can process scene text images (size of 128 × 32) at 34 fps and latency of 40 ms for pixelwise interpretation with the pixelwise classification accuracy over 90% on ICDAR-03 and ICDAR-13 dataset. The real energy-efficiency is 698 GOP/s/W and the peak energy-efficiency can get up to 7825 GOP/s/W. The proposed accelerator is 7 times more energy efficient than its optimized GPU-based implementation counterpart, while maintaining a real-time throughput with latency of 40 ms." @default.
• W2899272034 created "2018-11-09" @default.
• W2899272034 creator A5000387478 @default.
• W2899272034 creator A5013941213 @default.
• W2899272034 creator A5014057758 @default.
• W2899272034 creator A5034853402 @default.
• W2899272034 creator A5037178287 @default.
• W2899272034 creator A5042682339 @default.
• W2899272034 creator A5070756898 @default.
• W2899272034 creator A5083744126 @default.
• W2899272034 date "2019-09-01" @default.
• W2899272034 modified "2023-09-23" @default.
• W2899272034 title "A 34-FPS 698-GOP/s/W Binarized Deep Neural Network-Based Natural Scene Text Interpretation Accelerator for Mobile Edge Computing" @default.
• W2899272034 cites W1919191429 @default.
• W2899272034 cites W2019459561 @default.
• W2899272034 cites W2112796928 @default.
• W2899272034 cites W2122221966 @default.
• W2899272034 cites W2289252105 @default.
• W2899272034 cites W2300242332 @default.
• W2899272034 cites W2341386190 @default.
• W2899272034 cites W2548522351 @default.
• W2899272034 cites W2585546120 @default.
• W2899272034 cites W2605487586 @default.
• W2899272034 cites W2618530766 @default.
• W2899272034 cites W2919115771 @default.
• W2899272034 cites W2963030892 @default.
• W2899272034 cites W2963122961 @default.
• W2899272034 cites W2963145956 @default.
• W2899272034 cites W2963161243 @default.
• W2899272034 cites W2963881378 @default.
• W2899272034 cites W2963893493 @default.
• W2899272034 cites W70975097 @default.
• W2899272034 doi "https://doi.org/10.1109/tie.2018.2875643" @default.
• W2899272034 hasPublicationYear "2019" @default.
• W2899272034 type Work @default.
• W2899272034 sameAs 2899272034 @default.
• W2899272034 citedByCount "12" @default.
• W2899272034 countsByYear W28992720342019 @default.
• W2899272034 countsByYear W28992720342020 @default.
• W2899272034 countsByYear W28992720342021 @default.
• W2899272034 countsByYear W28992720342022 @default.
• W2899272034 countsByYear W28992720342023 @default.
• W2899272034 crossrefType "journal-article" @default.
• W2899272034 hasAuthorship W2899272034A5000387478 @default.
• W2899272034 hasAuthorship W2899272034A5013941213 @default.
• W2899272034 hasAuthorship W2899272034A5014057758 @default.
• W2899272034 hasAuthorship W2899272034A5034853402 @default.
• W2899272034 hasAuthorship W2899272034A5037178287 @default.
• W2899272034 hasAuthorship W2899272034A5042682339 @default.
• W2899272034 hasAuthorship W2899272034A5070756898 @default.
• W2899272034 hasAuthorship W2899272034A5083744126 @default.
• W2899272034 hasBestOaLocation W28992720341 @default.
• W2899272034 hasConcept C111919701 @default.
• W2899272034 hasConcept C154945302 @default.
• W2899272034 hasConcept C157764524 @default.
• W2899272034 hasConcept C160633673 @default.
• W2899272034 hasConcept C162307627 @default.
• W2899272034 hasConcept C173608175 @default.
• W2899272034 hasConcept C2778456923 @default.
• W2899272034 hasConcept C2779960059 @default.
• W2899272034 hasConcept C41008148 @default.
• W2899272034 hasConcept C555944384 @default.
• W2899272034 hasConcept C76155785 @default.
• W2899272034 hasConcept C81363708 @default.
• W2899272034 hasConcept C82876162 @default.
• W2899272034 hasConcept C9390403 @default.
• W2899272034 hasConceptScore W2899272034C111919701 @default.
• W2899272034 hasConceptScore W2899272034C154945302 @default.
• W2899272034 hasConceptScore W2899272034C157764524 @default.
• W2899272034 hasConceptScore W2899272034C160633673 @default.
• W2899272034 hasConceptScore W2899272034C162307627 @default.
• W2899272034 hasConceptScore W2899272034C173608175 @default.
• W2899272034 hasConceptScore W2899272034C2778456923 @default.
• W2899272034 hasConceptScore W2899272034C2779960059 @default.
• W2899272034 hasConceptScore W2899272034C41008148 @default.
• W2899272034 hasConceptScore W2899272034C555944384 @default.
• W2899272034 hasConceptScore W2899272034C76155785 @default.
• W2899272034 hasConceptScore W2899272034C81363708 @default.
• W2899272034 hasConceptScore W2899272034C82876162 @default.
• W2899272034 hasConceptScore W2899272034C9390403 @default.
• W2899272034 hasFunder F4320306076 @default.
• W2899272034 hasIssue "9" @default.
• W2899272034 hasLocation W28992720341 @default.
• W2899272034 hasOpenAccess W2899272034 @default.
• W2899272034 hasPrimaryLocation W28992720341 @default.
• W2899272034 hasRelatedWork W2047588290 @default.
• W2899272034 hasRelatedWork W2736305332 @default.
• W2899272034 hasRelatedWork W3131650874 @default.
• W2899272034 hasRelatedWork W3138718334 @default.
• W2899272034 hasRelatedWork W3184768109 @default.
• W2899272034 hasRelatedWork W4236142432 @default.
• W2899272034 hasRelatedWork W4237968029 @default.
• W2899272034 hasRelatedWork W4287076991 @default.
• W2899272034 hasRelatedWork W4293869292 @default.
• W2899272034 hasRelatedWork W4376106090 @default.
• W2899272034 hasVolume "66" @default.
• W2899272034 isParatext "false" @default.
• W2899272034 isRetracted "false" @default.

• next