FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381716448> ?p ?o ?g. }

• W4381716448 endingPage "3579" @default.
• W4381716448 startingPage "3567" @default.
• W4381716448 abstract "Neural video codecs have demonstrated great potential in video transmission and storage applications. Existing neural hybrid video coding approaches rely on optical flow or Gaussian-scale flow for prediction, which cannot support fine-grained adaptation to diverse motion content. Towards more content-adaptive prediction, we propose a novel cross-scale prediction module that achieves more effective motion compensation. Specifically, on the one hand, we produce a reference feature pyramid as prediction sources and then transmit cross-scale flows that leverage the feature scale to control the precision of prediction. On the other hand, for the first time, a weighted prediction mechanism is introduced even if only a single reference frame is available, which can help synthesize a fine prediction result by transmitting cross-scale weight maps. In addition to the cross-scale prediction module, we further propose a multi-stage quantization strategy, which improves the rate-distortion performance with no extra computational penalty during inference. We show the encouraging performance of our efficient neural video codec (ENVC) on several benchmark datasets. In particular, the proposed ENVC can compete with the latest coding standard H.266/VVC in terms of sRGB PSNR on UVG dataset for the low-latency mode. We also analyze in detail the effectiveness of the cross-scale prediction module in handling various video content, and provide a comprehensive ablation study to analyze those important components. Test code is available at https://github.com/USTC-IMCL/ENVC." @default.
• W4381716448 created "2023-06-24" @default.
• W4381716448 creator A5017613099 @default.
• W4381716448 creator A5019699241 @default.
• W4381716448 creator A5049237194 @default.
• W4381716448 creator A5062901935 @default.
• W4381716448 creator A5079572598 @default.
• W4381716448 date "2023-01-01" @default.
• W4381716448 modified "2023-10-16" @default.
• W4381716448 title "Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression" @default.
• W4381716448 cites W2048820076 @default.
• W4381716448 cites W2133665775 @default.
• W4381716448 cites W2140199336 @default.
• W4381716448 cites W2146395539 @default.
• W4381716448 cites W2163889646 @default.
• W4381716448 cites W2511458122 @default.
• W4381716448 cites W2565639579 @default.
• W4381716448 cites W2601564443 @default.
• W4381716448 cites W2798514732 @default.
• W4381716448 cites W2897872264 @default.
• W4381716448 cites W2963189365 @default.
• W4381716448 cites W2966926453 @default.
• W4381716448 cites W2969260367 @default.
• W4381716448 cites W2981613960 @default.
• W4381716448 cites W2982853315 @default.
• W4381716448 cites W2987947587 @default.
• W4381716448 cites W2992051623 @default.
• W4381716448 cites W3020741905 @default.
• W4381716448 cites W3031546776 @default.
• W4381716448 cites W3034469748 @default.
• W4381716448 cites W3034802763 @default.
• W4381716448 cites W3035195755 @default.
• W4381716448 cites W3035209157 @default.
• W4381716448 cites W3035302041 @default.
• W4381716448 cites W3095479355 @default.
• W4381716448 cites W3102015846 @default.
• W4381716448 cites W3107066575 @default.
• W4381716448 cites W3110286842 @default.
• W4381716448 cites W3116647679 @default.
• W4381716448 cites W3131427579 @default.
• W4381716448 cites W3138516171 @default.
• W4381716448 cites W3173272744 @default.
• W4381716448 cites W3179468628 @default.
• W4381716448 cites W3202918664 @default.
• W4381716448 cites W4206364355 @default.
• W4381716448 cites W4214743248 @default.
• W4381716448 cites W4214761665 @default.
• W4381716448 cites W4285483958 @default.
• W4381716448 cites W4312774595 @default.
• W4381716448 cites W4313058111 @default.
• W4381716448 doi "https://doi.org/10.1109/tip.2023.3287495" @default.
• W4381716448 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37347638" @default.
• W4381716448 hasPublicationYear "2023" @default.
• W4381716448 type Work @default.
• W4381716448 citedByCount "0" @default.
• W4381716448 crossrefType "journal-article" @default.
• W4381716448 hasAuthorship W4381716448A5017613099 @default.
• W4381716448 hasAuthorship W4381716448A5019699241 @default.
• W4381716448 hasAuthorship W4381716448A5049237194 @default.
• W4381716448 hasAuthorship W4381716448A5062901935 @default.
• W4381716448 hasAuthorship W4381716448A5079572598 @default.
• W4381716448 hasBestOaLocation W43817164482 @default.
• W4381716448 hasConcept C111919701 @default.
• W4381716448 hasConcept C118505674 @default.
• W4381716448 hasConcept C128840427 @default.
• W4381716448 hasConcept C153180895 @default.
• W4381716448 hasConcept C154945302 @default.
• W4381716448 hasConcept C161765866 @default.
• W4381716448 hasConcept C202474056 @default.
• W4381716448 hasConcept C23431618 @default.
• W4381716448 hasConcept C31972630 @default.
• W4381716448 hasConcept C41008148 @default.
• W4381716448 hasConcept C65483669 @default.
• W4381716448 hasConcept C78548338 @default.
• W4381716448 hasConcept C9390403 @default.
• W4381716448 hasConceptScore W4381716448C111919701 @default.
• W4381716448 hasConceptScore W4381716448C118505674 @default.
• W4381716448 hasConceptScore W4381716448C128840427 @default.
• W4381716448 hasConceptScore W4381716448C153180895 @default.
• W4381716448 hasConceptScore W4381716448C154945302 @default.
• W4381716448 hasConceptScore W4381716448C161765866 @default.
• W4381716448 hasConceptScore W4381716448C202474056 @default.
• W4381716448 hasConceptScore W4381716448C23431618 @default.
• W4381716448 hasConceptScore W4381716448C31972630 @default.
• W4381716448 hasConceptScore W4381716448C41008148 @default.
• W4381716448 hasConceptScore W4381716448C65483669 @default.
• W4381716448 hasConceptScore W4381716448C78548338 @default.
• W4381716448 hasConceptScore W4381716448C9390403 @default.
• W4381716448 hasFunder F4320321001 @default.
• W4381716448 hasLocation W43817164481 @default.
• W4381716448 hasLocation W43817164482 @default.
• W4381716448 hasLocation W43817164483 @default.
• W4381716448 hasOpenAccess W4381716448 @default.
• W4381716448 hasPrimaryLocation W43817164481 @default.
• W4381716448 hasRelatedWork W1525714949 @default.
• W4381716448 hasRelatedWork W1560709196 @default.
• W4381716448 hasRelatedWork W2029405403 @default.
• W4381716448 hasRelatedWork W2098572180 @default.

• next