Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378588773> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4378588773 endingPage "5133" @default.
- W4378588773 startingPage "5133" @default.
- W4378588773 abstract "This article proposes a video prediction network called STMP-Net that addresses the problem of the inability of Recurrent Neural Networks (RNNs) to fully extract spatiotemporal information and motion change features during video prediction. STMP-Net combines spatiotemporal memory and motion perception to make more accurate predictions. Firstly, a spatiotemporal attention fusion unit (STAFU) is proposed as the basic module of the prediction network, which learns and transfers spatiotemporal features in both horizontal and vertical directions based on spatiotemporal feature information and contextual attention mechanism. Additionally, a contextual attention mechanism is introduced in the hidden state to focus attention on more important details and improve the capture of detailed features, thus greatly reducing the computational load of the network. Secondly, a motion gradient highway unit (MGHU) is proposed by combining motion perception modules and adding them between adjacent layers, which can adaptively learn the important information of input features and fuse motion change features to significantly improve the predictive performance of the model. Finally, a high-speed channel is provided between layers to quickly transmit important features and alleviate the gradient vanishing problem caused by back-propagation. The experimental results show that compared with mainstream video prediction networks, the proposed method can achieve better prediction results in long-term video prediction, especially in motion scenes." @default.
- W4378588773 created "2023-05-28" @default.
- W4378588773 creator A5042507079 @default.
- W4378588773 creator A5066309268 @default.
- W4378588773 date "2023-05-28" @default.
- W4378588773 modified "2023-10-01" @default.
- W4378588773 title "STMP-Net: A Spatiotemporal Prediction Network Integrating Motion Perception" @default.
- W4378588773 cites W2036317923 @default.
- W4378588773 cites W2157331557 @default.
- W4378588773 cites W2522485430 @default.
- W4378588773 cites W2586480386 @default.
- W4378588773 cites W2769735038 @default.
- W4378588773 cites W2808011586 @default.
- W4378588773 cites W2883991972 @default.
- W4378588773 cites W2963610939 @default.
- W4378588773 cites W2964303162 @default.
- W4378588773 cites W2967033144 @default.
- W4378588773 cites W2999794487 @default.
- W4378588773 cites W3093657173 @default.
- W4378588773 cites W3138340468 @default.
- W4378588773 cites W3162748909 @default.
- W4378588773 cites W3174944154 @default.
- W4378588773 cites W3183430956 @default.
- W4378588773 cites W3184447318 @default.
- W4378588773 cites W3212567306 @default.
- W4378588773 cites W4210773761 @default.
- W4378588773 cites W4229368211 @default.
- W4378588773 cites W4249279051 @default.
- W4378588773 cites W4300862266 @default.
- W4378588773 cites W4312794305 @default.
- W4378588773 cites W4320008793 @default.
- W4378588773 cites W4365128550 @default.
- W4378588773 cites W4376620200 @default.
- W4378588773 doi "https://doi.org/10.3390/s23115133" @default.
- W4378588773 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37299860" @default.
- W4378588773 hasPublicationYear "2023" @default.
- W4378588773 type Work @default.
- W4378588773 citedByCount "0" @default.
- W4378588773 crossrefType "journal-article" @default.
- W4378588773 hasAuthorship W4378588773A5042507079 @default.
- W4378588773 hasAuthorship W4378588773A5066309268 @default.
- W4378588773 hasBestOaLocation W43785887731 @default.
- W4378588773 hasConcept C104114177 @default.
- W4378588773 hasConcept C119599485 @default.
- W4378588773 hasConcept C119857082 @default.
- W4378588773 hasConcept C127413603 @default.
- W4378588773 hasConcept C141353440 @default.
- W4378588773 hasConcept C153180895 @default.
- W4378588773 hasConcept C154945302 @default.
- W4378588773 hasConcept C169760540 @default.
- W4378588773 hasConcept C26760741 @default.
- W4378588773 hasConcept C31972630 @default.
- W4378588773 hasConcept C41008148 @default.
- W4378588773 hasConcept C50644808 @default.
- W4378588773 hasConcept C86803240 @default.
- W4378588773 hasConceptScore W4378588773C104114177 @default.
- W4378588773 hasConceptScore W4378588773C119599485 @default.
- W4378588773 hasConceptScore W4378588773C119857082 @default.
- W4378588773 hasConceptScore W4378588773C127413603 @default.
- W4378588773 hasConceptScore W4378588773C141353440 @default.
- W4378588773 hasConceptScore W4378588773C153180895 @default.
- W4378588773 hasConceptScore W4378588773C154945302 @default.
- W4378588773 hasConceptScore W4378588773C169760540 @default.
- W4378588773 hasConceptScore W4378588773C26760741 @default.
- W4378588773 hasConceptScore W4378588773C31972630 @default.
- W4378588773 hasConceptScore W4378588773C41008148 @default.
- W4378588773 hasConceptScore W4378588773C50644808 @default.
- W4378588773 hasConceptScore W4378588773C86803240 @default.
- W4378588773 hasIssue "11" @default.
- W4378588773 hasLocation W43785887731 @default.
- W4378588773 hasLocation W43785887732 @default.
- W4378588773 hasLocation W43785887733 @default.
- W4378588773 hasOpenAccess W4378588773 @default.
- W4378588773 hasPrimaryLocation W43785887731 @default.
- W4378588773 hasRelatedWork W2029249305 @default.
- W4378588773 hasRelatedWork W2115571026 @default.
- W4378588773 hasRelatedWork W2511137960 @default.
- W4378588773 hasRelatedWork W251639349 @default.
- W4378588773 hasRelatedWork W2604231787 @default.
- W4378588773 hasRelatedWork W2610014769 @default.
- W4378588773 hasRelatedWork W2687972263 @default.
- W4378588773 hasRelatedWork W2912737833 @default.
- W4378588773 hasRelatedWork W3214088465 @default.
- W4378588773 hasRelatedWork W4321142835 @default.
- W4378588773 hasVolume "23" @default.
- W4378588773 isParatext "false" @default.
- W4378588773 isRetracted "false" @default.
- W4378588773 workType "article" @default.