Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285392018> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4285392018 endingPage "701" @default.
- W4285392018 startingPage "699" @default.
- W4285392018 abstract "Recent studies in the field of video super-resolution (VSR) have taken great advantage of neural networks and achieved remarkable performance. However, current neural network-based VSR methods have the following two limitations: (1) sophisticated models usually have high computational overhead and require large caches to store intermediate feature maps and parameters. (2) Bidirectional RNN-based methods cannot perform VSR until a complete video sequence is available because of the back-propagation of hidden states. The above two shortcomings make the existing VSR models hard to achieve real-time VSR. To reduce the computational complexity of the network, the authors propose a lightweight hardware-efficient recurrent neural network model, LERN, which is combined with depthwise separable convolution and pixel unshuffle. An SRA block is also introduced to help the model get better VSR performance. In order to wisely exploit video inter-frame information without causing the back propagation of hidden states, the authors introduce a new recurrent architecture that is optimized for video sequences. Besides, the authors design a quantization algorithm to find the optimal fixed-point representations for each layer. Experimental results demonstrate that LERN can achieve excellent performance with low overhead." @default.
- W4285392018 created "2022-07-14" @default.
- W4285392018 creator A5071453879 @default.
- W4285392018 creator A5076706670 @default.
- W4285392018 creator A5083921108 @default.
- W4285392018 date "2022-07-13" @default.
- W4285392018 modified "2023-09-29" @default.
- W4285392018 title "A lightweight hardware‐efficient recurrent network for video super‐resolution" @default.
- W4285392018 cites W2476548250 @default.
- W4285392018 cites W2610638008 @default.
- W4285392018 cites W2798838583 @default.
- W4285392018 cites W2886623847 @default.
- W4285392018 cites W2904156796 @default.
- W4285392018 cites W2923834406 @default.
- W4285392018 cites W2963125010 @default.
- W4285392018 cites W2965669158 @default.
- W4285392018 cites W3111013938 @default.
- W4285392018 doi "https://doi.org/10.1049/ell2.12576" @default.
- W4285392018 hasPublicationYear "2022" @default.
- W4285392018 type Work @default.
- W4285392018 citedByCount "1" @default.
- W4285392018 countsByYear W42853920182023 @default.
- W4285392018 crossrefType "journal-article" @default.
- W4285392018 hasAuthorship W4285392018A5071453879 @default.
- W4285392018 hasAuthorship W4285392018A5076706670 @default.
- W4285392018 hasAuthorship W4285392018A5083921108 @default.
- W4285392018 hasBestOaLocation W42853920181 @default.
- W4285392018 hasConcept C111919701 @default.
- W4285392018 hasConcept C113775141 @default.
- W4285392018 hasConcept C11413529 @default.
- W4285392018 hasConcept C126042441 @default.
- W4285392018 hasConcept C147168706 @default.
- W4285392018 hasConcept C154945302 @default.
- W4285392018 hasConcept C165696696 @default.
- W4285392018 hasConcept C179799912 @default.
- W4285392018 hasConcept C2524010 @default.
- W4285392018 hasConcept C2777210771 @default.
- W4285392018 hasConcept C2779960059 @default.
- W4285392018 hasConcept C28855332 @default.
- W4285392018 hasConcept C31258907 @default.
- W4285392018 hasConcept C33923547 @default.
- W4285392018 hasConcept C38652104 @default.
- W4285392018 hasConcept C41008148 @default.
- W4285392018 hasConcept C50644808 @default.
- W4285392018 hasConcept C79403827 @default.
- W4285392018 hasConcept C9390403 @default.
- W4285392018 hasConceptScore W4285392018C111919701 @default.
- W4285392018 hasConceptScore W4285392018C113775141 @default.
- W4285392018 hasConceptScore W4285392018C11413529 @default.
- W4285392018 hasConceptScore W4285392018C126042441 @default.
- W4285392018 hasConceptScore W4285392018C147168706 @default.
- W4285392018 hasConceptScore W4285392018C154945302 @default.
- W4285392018 hasConceptScore W4285392018C165696696 @default.
- W4285392018 hasConceptScore W4285392018C179799912 @default.
- W4285392018 hasConceptScore W4285392018C2524010 @default.
- W4285392018 hasConceptScore W4285392018C2777210771 @default.
- W4285392018 hasConceptScore W4285392018C2779960059 @default.
- W4285392018 hasConceptScore W4285392018C28855332 @default.
- W4285392018 hasConceptScore W4285392018C31258907 @default.
- W4285392018 hasConceptScore W4285392018C33923547 @default.
- W4285392018 hasConceptScore W4285392018C38652104 @default.
- W4285392018 hasConceptScore W4285392018C41008148 @default.
- W4285392018 hasConceptScore W4285392018C50644808 @default.
- W4285392018 hasConceptScore W4285392018C79403827 @default.
- W4285392018 hasConceptScore W4285392018C9390403 @default.
- W4285392018 hasIssue "18" @default.
- W4285392018 hasLocation W42853920181 @default.
- W4285392018 hasOpenAccess W4285392018 @default.
- W4285392018 hasPrimaryLocation W42853920181 @default.
- W4285392018 hasRelatedWork W1998320603 @default.
- W4285392018 hasRelatedWork W2060665237 @default.
- W4285392018 hasRelatedWork W2162643069 @default.
- W4285392018 hasRelatedWork W2362064715 @default.
- W4285392018 hasRelatedWork W2373884999 @default.
- W4285392018 hasRelatedWork W2374646538 @default.
- W4285392018 hasRelatedWork W2642600425 @default.
- W4285392018 hasRelatedWork W3008102594 @default.
- W4285392018 hasRelatedWork W3093563898 @default.
- W4285392018 hasRelatedWork W3150190294 @default.
- W4285392018 hasVolume "58" @default.
- W4285392018 isParatext "false" @default.
- W4285392018 isRetracted "false" @default.
- W4285392018 workType "article" @default.