Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804935> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4385804935 abstract "Event camera pixels asynchronously output binary events corresponding to local light intensity changes in time. While encoding visual information in this fashion increases sparsity and the temporal detail of motion with respect to frame-based cameras, there is not yet an established machine learning method capable of exploiting these features to increase efficiency, reduce latency and, ultimately, perform optimally in event-based tasks. Graph neural networks are a promising avenue for such a method, but current solutions are too slow to be compatible with the continuous streaming nature of event-data. In this study, we propose a hemi-spherical update event-graph neural network that significantly reduces the complexity and latency of graph updating and event-level prediction. We compare our approach to existing graph neural network methods, as well as to dense-frame convolutional neural networks, on optical flow estimation tasks. Relative to the previous state of the art in event-graphs, we reduce event-graph update latency by more than four orders of magnitude and reduce the number of neural network calculations per second by 70× while predicting optical flow more accurately." @default.
- W4385804935 created "2023-08-15" @default.
- W4385804935 creator A5006902285 @default.
- W4385804935 creator A5031216442 @default.
- W4385804935 creator A5034609582 @default.
- W4385804935 creator A5039853755 @default.
- W4385804935 creator A5055024908 @default.
- W4385804935 creator A5089104859 @default.
- W4385804935 date "2023-06-01" @default.
- W4385804935 modified "2023-09-25" @default.
- W4385804935 title "HUGNet: Hemi-Spherical Update Graph Neural Network applied to low-latency event-based optical flow" @default.
- W4385804935 cites W1980178290 @default.
- W4385804935 cites W1998339166 @default.
- W4385804935 cites W2016574277 @default.
- W4385804935 cites W2016989767 @default.
- W4385804935 cites W2033959528 @default.
- W4385804935 cites W2076661751 @default.
- W4385804935 cites W2150355110 @default.
- W4385804935 cites W2153226019 @default.
- W4385804935 cites W2177690825 @default.
- W4385804935 cites W2513853720 @default.
- W4385804935 cites W2618530766 @default.
- W4385804935 cites W2768308213 @default.
- W4385804935 cites W2788172931 @default.
- W4385804935 cites W2883294120 @default.
- W4385804935 cites W2898323475 @default.
- W4385804935 cites W2904275768 @default.
- W4385804935 cites W2963182550 @default.
- W4385804935 cites W2981539886 @default.
- W4385804935 cites W3010268791 @default.
- W4385804935 cites W3015932348 @default.
- W4385804935 cites W3034657761 @default.
- W4385804935 cites W3092083701 @default.
- W4385804935 cites W3097980825 @default.
- W4385804935 cites W3102087395 @default.
- W4385804935 cites W3102178346 @default.
- W4385804935 cites W3200334356 @default.
- W4385804935 cites W4205982568 @default.
- W4385804935 cites W4308197356 @default.
- W4385804935 cites W4312281374 @default.
- W4385804935 cites W4313029475 @default.
- W4385804935 cites W4360605748 @default.
- W4385804935 doi "https://doi.org/10.1109/cvprw59228.2023.00411" @default.
- W4385804935 hasPublicationYear "2023" @default.
- W4385804935 type Work @default.
- W4385804935 citedByCount "0" @default.
- W4385804935 crossrefType "proceedings-article" @default.
- W4385804935 hasAuthorship W4385804935A5006902285 @default.
- W4385804935 hasAuthorship W4385804935A5031216442 @default.
- W4385804935 hasAuthorship W4385804935A5034609582 @default.
- W4385804935 hasAuthorship W4385804935A5039853755 @default.
- W4385804935 hasAuthorship W4385804935A5055024908 @default.
- W4385804935 hasAuthorship W4385804935A5089104859 @default.
- W4385804935 hasConcept C11413529 @default.
- W4385804935 hasConcept C115961682 @default.
- W4385804935 hasConcept C132525143 @default.
- W4385804935 hasConcept C153180895 @default.
- W4385804935 hasConcept C154945302 @default.
- W4385804935 hasConcept C155542232 @default.
- W4385804935 hasConcept C41008148 @default.
- W4385804935 hasConcept C50644808 @default.
- W4385804935 hasConcept C76155785 @default.
- W4385804935 hasConcept C80444323 @default.
- W4385804935 hasConcept C82876162 @default.
- W4385804935 hasConceptScore W4385804935C11413529 @default.
- W4385804935 hasConceptScore W4385804935C115961682 @default.
- W4385804935 hasConceptScore W4385804935C132525143 @default.
- W4385804935 hasConceptScore W4385804935C153180895 @default.
- W4385804935 hasConceptScore W4385804935C154945302 @default.
- W4385804935 hasConceptScore W4385804935C155542232 @default.
- W4385804935 hasConceptScore W4385804935C41008148 @default.
- W4385804935 hasConceptScore W4385804935C50644808 @default.
- W4385804935 hasConceptScore W4385804935C76155785 @default.
- W4385804935 hasConceptScore W4385804935C80444323 @default.
- W4385804935 hasConceptScore W4385804935C82876162 @default.
- W4385804935 hasLocation W43858049351 @default.
- W4385804935 hasOpenAccess W4385804935 @default.
- W4385804935 hasPrimaryLocation W43858049351 @default.
- W4385804935 hasRelatedWork W1987753576 @default.
- W4385804935 hasRelatedWork W2033914206 @default.
- W4385804935 hasRelatedWork W2146076056 @default.
- W4385804935 hasRelatedWork W2163831990 @default.
- W4385804935 hasRelatedWork W2380362089 @default.
- W4385804935 hasRelatedWork W2386387936 @default.
- W4385804935 hasRelatedWork W2726222394 @default.
- W4385804935 hasRelatedWork W3033499831 @default.
- W4385804935 hasRelatedWork W3196628752 @default.
- W4385804935 hasRelatedWork W2779562428 @default.
- W4385804935 isParatext "false" @default.
- W4385804935 isRetracted "false" @default.
- W4385804935 workType "article" @default.