Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887754865> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2887754865 endingPage "634" @default.
- W2887754865 startingPage "624" @default.
- W2887754865 abstract "Inspired by the success of deep convolutional neural networks (CNNs) with back-propagation (BP) training on large-scale image recognition tasks, recent research efforts concentrated on expending deep CNNs toward more challenging automatized video analysis, such as video classification, object tracking, action recognition and optical flow detection. Video comprises a sequence of images (frames) captured over time in which image data is a function of space and time. Extracting three-dimensional spatial-temporal features from multiple frames becomes a key ingredient for capturing and incorporating appearance and dynamic representations using deep CNNs. Hence, training deep CNNs on video involves significant computational resources and energy consumption due to extended number of frames across the time line of video length. We propose DeltaFrame-BP, a deep learning algorithm, which significantly reduces computational cost and energy consumption without accuracy degradation by streaming frame differences for deep CNNs training and inference. The inherent similarity between video frames due to high fps (frames per second) in video recording helps achieving high-sparsity and low-dynamic range data streaming using frame differences in comparison with raw video frames. According to our simulation, nearly 25 percent energy reduction was achieved in training using the proposed accuracy-lossless DeltaFrame-BP algorithm in comparison with the standard Back-propagation algorithm." @default.
- W2887754865 created "2018-08-22" @default.
- W2887754865 creator A5031161187 @default.
- W2887754865 creator A5044384604 @default.
- W2887754865 date "2018-10-01" @default.
- W2887754865 modified "2023-10-17" @default.
- W2887754865 title "DeltaFrame-BP: An Algorithm Using Frame Difference for Deep Convolutional Neural Networks Training and Inference on Video Data" @default.
- W2887754865 cites W1578285471 @default.
- W2887754865 cites W1963882359 @default.
- W2887754865 cites W2016053056 @default.
- W2887754865 cites W2051825853 @default.
- W2887754865 cites W2091902424 @default.
- W2887754865 cites W2116064496 @default.
- W2887754865 cites W2117539524 @default.
- W2887754865 cites W2136922672 @default.
- W2887754865 cites W2147253850 @default.
- W2887754865 cites W2280226538 @default.
- W2887754865 cites W2285660444 @default.
- W2887754865 cites W2334564994 @default.
- W2887754865 cites W2340897893 @default.
- W2887754865 cites W2342662179 @default.
- W2887754865 cites W2404427863 @default.
- W2887754865 cites W2605366333 @default.
- W2887754865 cites W2606822607 @default.
- W2887754865 cites W2613736958 @default.
- W2887754865 cites W2736237086 @default.
- W2887754865 cites W2760655081 @default.
- W2887754865 cites W4236788275 @default.
- W2887754865 cites W4301910720 @default.
- W2887754865 doi "https://doi.org/10.1109/tmscs.2018.2865303" @default.
- W2887754865 hasPublicationYear "2018" @default.
- W2887754865 type Work @default.
- W2887754865 sameAs 2887754865 @default.
- W2887754865 citedByCount "5" @default.
- W2887754865 countsByYear W28877548652020 @default.
- W2887754865 countsByYear W28877548652022 @default.
- W2887754865 crossrefType "journal-article" @default.
- W2887754865 hasAuthorship W2887754865A5031161187 @default.
- W2887754865 hasAuthorship W2887754865A5044384604 @default.
- W2887754865 hasBestOaLocation W28877548651 @default.
- W2887754865 hasConcept C108583219 @default.
- W2887754865 hasConcept C11413529 @default.
- W2887754865 hasConcept C119857082 @default.
- W2887754865 hasConcept C121332964 @default.
- W2887754865 hasConcept C126042441 @default.
- W2887754865 hasConcept C153180895 @default.
- W2887754865 hasConcept C153294291 @default.
- W2887754865 hasConcept C154945302 @default.
- W2887754865 hasConcept C2776214188 @default.
- W2887754865 hasConcept C2777211547 @default.
- W2887754865 hasConcept C41008148 @default.
- W2887754865 hasConcept C50644808 @default.
- W2887754865 hasConcept C51632099 @default.
- W2887754865 hasConcept C76155785 @default.
- W2887754865 hasConcept C81363708 @default.
- W2887754865 hasConceptScore W2887754865C108583219 @default.
- W2887754865 hasConceptScore W2887754865C11413529 @default.
- W2887754865 hasConceptScore W2887754865C119857082 @default.
- W2887754865 hasConceptScore W2887754865C121332964 @default.
- W2887754865 hasConceptScore W2887754865C126042441 @default.
- W2887754865 hasConceptScore W2887754865C153180895 @default.
- W2887754865 hasConceptScore W2887754865C153294291 @default.
- W2887754865 hasConceptScore W2887754865C154945302 @default.
- W2887754865 hasConceptScore W2887754865C2776214188 @default.
- W2887754865 hasConceptScore W2887754865C2777211547 @default.
- W2887754865 hasConceptScore W2887754865C41008148 @default.
- W2887754865 hasConceptScore W2887754865C50644808 @default.
- W2887754865 hasConceptScore W2887754865C51632099 @default.
- W2887754865 hasConceptScore W2887754865C76155785 @default.
- W2887754865 hasConceptScore W2887754865C81363708 @default.
- W2887754865 hasFunder F4320306087 @default.
- W2887754865 hasFunder F4320307102 @default.
- W2887754865 hasFunder F4320335353 @default.
- W2887754865 hasIssue "4" @default.
- W2887754865 hasLocation W28877548651 @default.
- W2887754865 hasOpenAccess W2887754865 @default.
- W2887754865 hasPrimaryLocation W28877548651 @default.
- W2887754865 hasRelatedWork W2337926734 @default.
- W2887754865 hasRelatedWork W2732542196 @default.
- W2887754865 hasRelatedWork W2738221750 @default.
- W2887754865 hasRelatedWork W2963958939 @default.
- W2887754865 hasRelatedWork W3021430260 @default.
- W2887754865 hasRelatedWork W3136076031 @default.
- W2887754865 hasRelatedWork W3156786002 @default.
- W2887754865 hasRelatedWork W4311257506 @default.
- W2887754865 hasRelatedWork W4313289428 @default.
- W2887754865 hasRelatedWork W564581980 @default.
- W2887754865 hasVolume "4" @default.
- W2887754865 isParatext "false" @default.
- W2887754865 isRetracted "false" @default.
- W2887754865 magId "2887754865" @default.
- W2887754865 workType "article" @default.