Matches in SemOpenAlex for { <https://semopenalex.org/work/W2981878426> ?p ?o ?g. }
- W2981878426 abstract "Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single neighboring frame or a pair of neighboring frames (preceding and/or following the target frame) for this task. Furthermore, as frames of high quality overall may contain low-quality patches, and high-quality patches may exist in frames of low quality overall, current methods focusing on nearby peak-quality frames (PQFs) may miss high-quality details in low-quality frames. To remedy these shortcomings, in this paper we propose a novel end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTM in short) that exploits multiple consecutive frames. An approximate non-local strategy is introduced in NL-ConvLSTM to capture global motion patterns and trace the spatiotemporal dependency in a video sequence. This approximate strategy makes the non-local module work in a fast and low space-cost way. Our method uses the preceding and following frames of the target frame to generate a residual, from which a higher quality frame is reconstructed. Experiments on two datasets show that NL-ConvLSTM outperforms the existing methods." @default.
- W2981878426 created "2019-11-01" @default.
- W2981878426 creator A5017145972 @default.
- W2981878426 creator A5017862559 @default.
- W2981878426 creator A5018343158 @default.
- W2981878426 creator A5029306322 @default.
- W2981878426 creator A5034513950 @default.
- W2981878426 date "2019-10-27" @default.
- W2981878426 modified "2023-09-23" @default.
- W2981878426 title "Non-Local ConvLSTM for Video Compression Artifact Reduction" @default.
- W2981878426 cites W1485009520 @default.
- W2981878426 cites W1946766895 @default.
- W2981878426 cites W1978280057 @default.
- W2981878426 cites W1984077106 @default.
- W2981878426 cites W2056370875 @default.
- W2981878426 cites W2085758610 @default.
- W2981878426 cites W2097073572 @default.
- W2981878426 cites W2114586165 @default.
- W2981878426 cites W2117539524 @default.
- W2981878426 cites W2127292171 @default.
- W2981878426 cites W2141620200 @default.
- W2981878426 cites W2142683286 @default.
- W2981878426 cites W2146395539 @default.
- W2981878426 cites W2163605009 @default.
- W2981878426 cites W2320725294 @default.
- W2981878426 cites W2345337169 @default.
- W2981878426 cites W2508457857 @default.
- W2981878426 cites W2519021537 @default.
- W2981878426 cites W2553668389 @default.
- W2981878426 cites W2557227117 @default.
- W2981878426 cites W2604885021 @default.
- W2981878426 cites W2612222456 @default.
- W2981878426 cites W2613155248 @default.
- W2981878426 cites W2752154940 @default.
- W2981878426 cites W2753574358 @default.
- W2981878426 cites W2753778655 @default.
- W2981878426 cites W2757828535 @default.
- W2981878426 cites W2781335552 @default.
- W2981878426 cites W2798309955 @default.
- W2981878426 cites W2798664922 @default.
- W2981878426 cites W2890577598 @default.
- W2981878426 cites W2891179842 @default.
- W2981878426 cites W2895361760 @default.
- W2981878426 cites W2895957955 @default.
- W2981878426 cites W2915260409 @default.
- W2981878426 cites W2962687329 @default.
- W2981878426 cites W2962737939 @default.
- W2981878426 cites W2962927175 @default.
- W2981878426 cites W2962935835 @default.
- W2981878426 cites W2963091558 @default.
- W2981878426 cites W2963391718 @default.
- W2981878426 cites W2963866658 @default.
- W2981878426 cites W2964040059 @default.
- W2981878426 cites W2964046669 @default.
- W2981878426 cites W2964121744 @default.
- W2981878426 cites W2964125708 @default.
- W2981878426 cites W2964196857 @default.
- W2981878426 cites W3100087914 @default.
- W2981878426 cites W3102015846 @default.
- W2981878426 doi "https://doi.org/10.48550/arxiv.1910.12286" @default.
- W2981878426 hasPublicationYear "2019" @default.
- W2981878426 type Work @default.
- W2981878426 sameAs 2981878426 @default.
- W2981878426 citedByCount "1" @default.
- W2981878426 countsByYear W29818784262021 @default.
- W2981878426 crossrefType "posted-content" @default.
- W2981878426 hasAuthorship W2981878426A5017145972 @default.
- W2981878426 hasAuthorship W2981878426A5017862559 @default.
- W2981878426 hasAuthorship W2981878426A5018343158 @default.
- W2981878426 hasAuthorship W2981878426A5029306322 @default.
- W2981878426 hasAuthorship W2981878426A5034513950 @default.
- W2981878426 hasBestOaLocation W29818784261 @default.
- W2981878426 hasConcept C111335779 @default.
- W2981878426 hasConcept C111472728 @default.
- W2981878426 hasConcept C115961682 @default.
- W2981878426 hasConcept C126042441 @default.
- W2981878426 hasConcept C12713177 @default.
- W2981878426 hasConcept C13481523 @default.
- W2981878426 hasConcept C138885662 @default.
- W2981878426 hasConcept C153180895 @default.
- W2981878426 hasConcept C154945302 @default.
- W2981878426 hasConcept C172849965 @default.
- W2981878426 hasConcept C19768560 @default.
- W2981878426 hasConcept C204641915 @default.
- W2981878426 hasConcept C2524010 @default.
- W2981878426 hasConcept C2779010991 @default.
- W2981878426 hasConcept C2779530757 @default.
- W2981878426 hasConcept C31972630 @default.
- W2981878426 hasConcept C33923547 @default.
- W2981878426 hasConcept C39394851 @default.
- W2981878426 hasConcept C41008148 @default.
- W2981878426 hasConcept C57654395 @default.
- W2981878426 hasConcept C76155785 @default.
- W2981878426 hasConcept C9417928 @default.
- W2981878426 hasConceptScore W2981878426C111335779 @default.
- W2981878426 hasConceptScore W2981878426C111472728 @default.
- W2981878426 hasConceptScore W2981878426C115961682 @default.
- W2981878426 hasConceptScore W2981878426C126042441 @default.
- W2981878426 hasConceptScore W2981878426C12713177 @default.
- W2981878426 hasConceptScore W2981878426C13481523 @default.