Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223559274> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4223559274 endingPage "170" @default.
- W4223559274 startingPage "160" @default.
- W4223559274 abstract "The spatial-temporal sequence prediction task is a challenge for neural networks, as it requires capturing temporal and spatial changes simultaneously. Recent researches focus on the modification of the ConvLSTM internal elements, which improves the prediction ability to some extent but introduces a large number of parameters. We observe that although the result generated by the row ConvLSTM is not very accurate in position and have a blurry appearance, it contains enough elements required to reconstruct the prediction. The motivation is to further refine these feature maps. Therefore, we propose a multi-attention LSTM (MA-LSTM) based on dimensional decoupling attention to alleviate the problems of the existing ConvLSTM-based methods, including inaccurate positions prediction and blurry generated results. The proposed model includes the Dimensionality Decoupling Module (D2M) and the Channel Attention Module (CAM). D2M compresses dimensions to transfer motion features over time that squeezes the features by dimensions and calculates the motion distribution of each dimension. CAM maintains the predicted texture information, which integrates latent information between channels and weights of the effective channels. Through the coordination of multiple modes, the model has long-term predictive capability and the accuracy of the prediction results has been improved. Experimental results show that using a smaller number of parameters, the proposed method can obtain competitive results but less inference time compared with the state-of-the-art (SOTA) methods." @default.
- W4223559274 created "2022-04-15" @default.
- W4223559274 creator A5006008836 @default.
- W4223559274 creator A5017938531 @default.
- W4223559274 creator A5022757746 @default.
- W4223559274 creator A5058134073 @default.
- W4223559274 creator A5070021804 @default.
- W4223559274 date "2022-07-01" @default.
- W4223559274 modified "2023-09-27" @default.
- W4223559274 title "Dimension decoupling attention mechanism for time series prediction" @default.
- W4223559274 cites W2064675550 @default.
- W4223559274 cites W2110485445 @default.
- W4223559274 cites W2133665775 @default.
- W4223559274 cites W2194775991 @default.
- W4223559274 cites W2549139847 @default.
- W4223559274 cites W2575842049 @default.
- W4223559274 cites W2737725206 @default.
- W4223559274 cites W2891859485 @default.
- W4223559274 cites W2904988869 @default.
- W4223559274 cites W2907228515 @default.
- W4223559274 cites W2922509574 @default.
- W4223559274 cites W2963246338 @default.
- W4223559274 cites W2963420686 @default.
- W4223559274 cites W2963495494 @default.
- W4223559274 cites W2964931564 @default.
- W4223559274 cites W2972940264 @default.
- W4223559274 cites W3019918961 @default.
- W4223559274 cites W3034421924 @default.
- W4223559274 cites W3034552520 @default.
- W4223559274 cites W3177349073 @default.
- W4223559274 cites W3199196998 @default.
- W4223559274 cites W4249279051 @default.
- W4223559274 cites W4287331249 @default.
- W4223559274 cites W4307339397 @default.
- W4223559274 doi "https://doi.org/10.1016/j.neucom.2022.04.063" @default.
- W4223559274 hasPublicationYear "2022" @default.
- W4223559274 type Work @default.
- W4223559274 citedByCount "2" @default.
- W4223559274 countsByYear W42235592742022 @default.
- W4223559274 countsByYear W42235592742023 @default.
- W4223559274 crossrefType "journal-article" @default.
- W4223559274 hasAuthorship W4223559274A5006008836 @default.
- W4223559274 hasAuthorship W4223559274A5017938531 @default.
- W4223559274 hasAuthorship W4223559274A5022757746 @default.
- W4223559274 hasAuthorship W4223559274A5058134073 @default.
- W4223559274 hasAuthorship W4223559274A5070021804 @default.
- W4223559274 hasConcept C111030470 @default.
- W4223559274 hasConcept C119857082 @default.
- W4223559274 hasConcept C127413603 @default.
- W4223559274 hasConcept C133731056 @default.
- W4223559274 hasConcept C153180895 @default.
- W4223559274 hasConcept C154945302 @default.
- W4223559274 hasConcept C202444582 @default.
- W4223559274 hasConcept C205606062 @default.
- W4223559274 hasConcept C2776214188 @default.
- W4223559274 hasConcept C33676613 @default.
- W4223559274 hasConcept C33923547 @default.
- W4223559274 hasConcept C41008148 @default.
- W4223559274 hasConcept C70518039 @default.
- W4223559274 hasConceptScore W4223559274C111030470 @default.
- W4223559274 hasConceptScore W4223559274C119857082 @default.
- W4223559274 hasConceptScore W4223559274C127413603 @default.
- W4223559274 hasConceptScore W4223559274C133731056 @default.
- W4223559274 hasConceptScore W4223559274C153180895 @default.
- W4223559274 hasConceptScore W4223559274C154945302 @default.
- W4223559274 hasConceptScore W4223559274C202444582 @default.
- W4223559274 hasConceptScore W4223559274C205606062 @default.
- W4223559274 hasConceptScore W4223559274C2776214188 @default.
- W4223559274 hasConceptScore W4223559274C33676613 @default.
- W4223559274 hasConceptScore W4223559274C33923547 @default.
- W4223559274 hasConceptScore W4223559274C41008148 @default.
- W4223559274 hasConceptScore W4223559274C70518039 @default.
- W4223559274 hasFunder F4320321001 @default.
- W4223559274 hasFunder F4320335953 @default.
- W4223559274 hasLocation W42235592741 @default.
- W4223559274 hasOpenAccess W4223559274 @default.
- W4223559274 hasPrimaryLocation W42235592741 @default.
- W4223559274 hasRelatedWork W1520675566 @default.
- W4223559274 hasRelatedWork W1965275221 @default.
- W4223559274 hasRelatedWork W2066259560 @default.
- W4223559274 hasRelatedWork W2110350792 @default.
- W4223559274 hasRelatedWork W2158704926 @default.
- W4223559274 hasRelatedWork W2172836935 @default.
- W4223559274 hasRelatedWork W2355203151 @default.
- W4223559274 hasRelatedWork W3110687914 @default.
- W4223559274 hasRelatedWork W398889120 @default.
- W4223559274 hasRelatedWork W4214747999 @default.
- W4223559274 hasVolume "494" @default.
- W4223559274 isParatext "false" @default.
- W4223559274 isRetracted "false" @default.
- W4223559274 workType "article" @default.