FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280498095> ?p ?o ?g. }

• W4280498095 endingPage "102786" @default.
• W4280498095 startingPage "102786" @default.
• W4280498095 abstract "Graph convolution networks (GCNs) have been proven powerful in describing unstructured data. Currently, most of existing GCNs aim on more accuracy by constructing deeper models. However, these methods show limited benefits, and they often suffer from the common drawbacks brought by deep networks, such as large model size, high memory consumption and slow training speed. In this paper, different from these methods, we widen GCNs to improve the descriptiveness by expanding the width of input to avoid the above drawbacks. Specifically, we present a wider GCNs based model, WGNet, for 3D point cloud classification. A local dilated connecting (LDC) module is designed to obtain the adjacency matrix, while a context information aware (CIA) module is proposed to generate initial node representation. These two modules provide a way to transform 3D point cloud into graph structure with larger receptive field and rich initial node features. These two properties widen the channels of input and provide more rich information to describe the samples precisely. Besides, we provide analysis to formulate the above idea as the sample precision description. Then, we adopt ChebyNet as our basic network, and present a skip-connection-based GCNs to improve efficiency of feature reuse. WGNet was evaluated on two datasets. One was acquired by a mobile laser scanning system under the real road environments, while the other was the well-known public artificial dataset, ModelNet40. Experimental results show that WGNet achieves better performance than the state-of-the-art in terms of descriptiveness, efficiency and robustness. Ablation studies also demonstrate the effectiveness of our designed LDC and CIA modules." @default.
• W4280498095 created "2022-05-22" @default.
• W4280498095 creator A5007144110 @default.
• W4280498095 creator A5019025841 @default.
• W4280498095 creator A5028467654 @default.
• W4280498095 creator A5031606307 @default.
• W4280498095 creator A5035099734 @default.
• W4280498095 creator A5061899878 @default.
• W4280498095 creator A5065463441 @default.
• W4280498095 creator A5078988375 @default.
• W4280498095 creator A5084025577 @default.
• W4280498095 date "2022-06-01" @default.
• W4280498095 modified "2023-10-06" @default.
• W4280498095 title "WGNet: Wider graph convolution networks for 3D point cloud classification with local dilated connecting and context-aware" @default.
• W4280498095 cites W2076280802 @default.
• W4280498095 cites W2099606917 @default.
• W4280498095 cites W2164832577 @default.
• W4280498095 cites W2460657278 @default.
• W4280498095 cites W2890848214 @default.
• W4280498095 cites W2914608630 @default.
• W4280498095 cites W2963333168 @default.
• W4280498095 cites W2963446712 @default.
• W4280498095 cites W2969993800 @default.
• W4280498095 cites W2979750740 @default.
• W4280498095 cites W3000937247 @default.
• W4280498095 cites W3034428269 @default.
• W4280498095 cites W3039448353 @default.
• W4280498095 cites W3101921002 @default.
• W4280498095 cites W3197949924 @default.
• W4280498095 doi "https://doi.org/10.1016/j.jag.2022.102786" @default.
• W4280498095 hasPublicationYear "2022" @default.
• W4280498095 type Work @default.
• W4280498095 citedByCount "2" @default.
• W4280498095 countsByYear W42804980952022 @default.
• W4280498095 countsByYear W42804980952023 @default.
• W4280498095 crossrefType "journal-article" @default.
• W4280498095 hasAuthorship W4280498095A5007144110 @default.
• W4280498095 hasAuthorship W4280498095A5019025841 @default.
• W4280498095 hasAuthorship W4280498095A5028467654 @default.
• W4280498095 hasAuthorship W4280498095A5031606307 @default.
• W4280498095 hasAuthorship W4280498095A5035099734 @default.
• W4280498095 hasAuthorship W4280498095A5061899878 @default.
• W4280498095 hasAuthorship W4280498095A5065463441 @default.
• W4280498095 hasAuthorship W4280498095A5078988375 @default.
• W4280498095 hasAuthorship W4280498095A5084025577 @default.
• W4280498095 hasBestOaLocation W42804980951 @default.
• W4280498095 hasConcept C104317684 @default.
• W4280498095 hasConcept C110484373 @default.
• W4280498095 hasConcept C111919701 @default.
• W4280498095 hasConcept C113775141 @default.
• W4280498095 hasConcept C11413529 @default.
• W4280498095 hasConcept C119857082 @default.
• W4280498095 hasConcept C124101348 @default.
• W4280498095 hasConcept C127413603 @default.
• W4280498095 hasConcept C131979681 @default.
• W4280498095 hasConcept C132525143 @default.
• W4280498095 hasConcept C154945302 @default.
• W4280498095 hasConcept C180356752 @default.
• W4280498095 hasConcept C185592680 @default.
• W4280498095 hasConcept C206588197 @default.
• W4280498095 hasConcept C41008148 @default.
• W4280498095 hasConcept C548081761 @default.
• W4280498095 hasConcept C55493867 @default.
• W4280498095 hasConcept C63479239 @default.
• W4280498095 hasConcept C79974875 @default.
• W4280498095 hasConcept C80444323 @default.
• W4280498095 hasConceptScore W4280498095C104317684 @default.
• W4280498095 hasConceptScore W4280498095C110484373 @default.
• W4280498095 hasConceptScore W4280498095C111919701 @default.
• W4280498095 hasConceptScore W4280498095C113775141 @default.
• W4280498095 hasConceptScore W4280498095C11413529 @default.
• W4280498095 hasConceptScore W4280498095C119857082 @default.
• W4280498095 hasConceptScore W4280498095C124101348 @default.
• W4280498095 hasConceptScore W4280498095C127413603 @default.
• W4280498095 hasConceptScore W4280498095C131979681 @default.
• W4280498095 hasConceptScore W4280498095C132525143 @default.
• W4280498095 hasConceptScore W4280498095C154945302 @default.
• W4280498095 hasConceptScore W4280498095C180356752 @default.
• W4280498095 hasConceptScore W4280498095C185592680 @default.
• W4280498095 hasConceptScore W4280498095C206588197 @default.
• W4280498095 hasConceptScore W4280498095C41008148 @default.
• W4280498095 hasConceptScore W4280498095C548081761 @default.
• W4280498095 hasConceptScore W4280498095C55493867 @default.
• W4280498095 hasConceptScore W4280498095C63479239 @default.
• W4280498095 hasConceptScore W4280498095C79974875 @default.
• W4280498095 hasConceptScore W4280498095C80444323 @default.
• W4280498095 hasLocation W42804980951 @default.
• W4280498095 hasLocation W42804980952 @default.
• W4280498095 hasOpenAccess W4280498095 @default.
• W4280498095 hasPrimaryLocation W42804980951 @default.
• W4280498095 hasRelatedWork W125803343 @default.
• W4280498095 hasRelatedWork W1991172810 @default.
• W4280498095 hasRelatedWork W2059018062 @default.
• W4280498095 hasRelatedWork W2153421018 @default.
• W4280498095 hasRelatedWork W2369410163 @default.
• W4280498095 hasRelatedWork W2564285047 @default.
• W4280498095 hasRelatedWork W2604585036 @default.
• W4280498095 hasRelatedWork W2982430984 @default.

• next