FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292560147> ?p ?o ?g. }

• W4292560147 endingPage "12" @default.
• W4292560147 startingPage "1" @default.
• W4292560147 abstract "Deep convolutional networks have better smoke recognition performance. However, a lightweight network model and high recognition accuracy cannot be balanced when deployed on hardware with limited computing resources such as edge computing. Based on this background, we propose a novel smoke recognition network that combines convolutional networks (CNN) and self-attention. The core ideas of this framework are as follows: (1) Combine the depthwise convolution and asymmetric convolution of large convolution kernels to construct a lightweight CNN model, and realize multiscale extraction of feature information with slight model complexity. (2) Combined with the self-attention in transformer, a skip-connection branch is designed, which improves the feature extraction capability of the backbone network through parallel processing and fusion of feature map information. (3) Fusion multicomponent discrete cosine transform (DCT) is used to compress channel information and expand the ability of global average pooling (GAP) to aggregate feature maps. The proposed DCT-GAP improves the accuracy of the network without adding additional computational costs. Experimental results show that the proposed CSANet achieves an average accuracy of over 98.3% with 238 M FLOPs and 5.8 M parameters on the homemade smoke dataset, outperforming state-of-the-art competitors." @default.
• W4292560147 created "2022-08-22" @default.
• W4292560147 creator A5033114960 @default.
• W4292560147 creator A5041045472 @default.
• W4292560147 creator A5054570339 @default.
• W4292560147 creator A5061357989 @default.
• W4292560147 creator A5064524500 @default.
• W4292560147 creator A5083419467 @default.
• W4292560147 date "2022-08-21" @default.
• W4292560147 modified "2023-09-26" @default.
• W4292560147 title "Lightweight Smoke Recognition Based on Deep Convolution and Self-Attention" @default.
• W4292560147 cites W2097117768 @default.
• W4292560147 cites W2183341477 @default.
• W4292560147 cites W2194775991 @default.
• W4292560147 cites W2409822643 @default.
• W4292560147 cites W2751420734 @default.
• W4292560147 cites W2752782242 @default.
• W4292560147 cites W2883780447 @default.
• W4292560147 cites W2893520743 @default.
• W4292560147 cites W2901853555 @default.
• W4292560147 cites W2913895065 @default.
• W4292560147 cites W2944039629 @default.
• W4292560147 cites W2963163009 @default.
• W4292560147 cites W2963446712 @default.
• W4292560147 cites W2977616508 @default.
• W4292560147 cites W2982083293 @default.
• W4292560147 cites W2985488694 @default.
• W4292560147 cites W3034771037 @default.
• W4292560147 cites W3035414587 @default.
• W4292560147 cites W3088106384 @default.
• W4292560147 cites W3094710748 @default.
• W4292560147 cites W3110232229 @default.
• W4292560147 cites W3121523901 @default.
• W4292560147 cites W3131500599 @default.
• W4292560147 cites W3137278571 @default.
• W4292560147 cites W3159605905 @default.
• W4292560147 cites W3169473016 @default.
• W4292560147 cites W4205321420 @default.
• W4292560147 cites W4210252168 @default.
• W4292560147 cites W4210704852 @default.
• W4292560147 cites W4210932666 @default.
• W4292560147 cites W4213019189 @default.
• W4292560147 cites W4214630075 @default.
• W4292560147 cites W4214666412 @default.
• W4292560147 cites W4220980210 @default.
• W4292560147 cites W4226046733 @default.
• W4292560147 cites W4283589953 @default.
• W4292560147 cites W4313007769 @default.
• W4292560147 doi "https://doi.org/10.1155/2022/1218713" @default.
• W4292560147 hasPublicationYear "2022" @default.
• W4292560147 type Work @default.
• W4292560147 citedByCount "0" @default.
• W4292560147 crossrefType "journal-article" @default.
• W4292560147 hasAuthorship W4292560147A5033114960 @default.
• W4292560147 hasAuthorship W4292560147A5041045472 @default.
• W4292560147 hasAuthorship W4292560147A5054570339 @default.
• W4292560147 hasAuthorship W4292560147A5061357989 @default.
• W4292560147 hasAuthorship W4292560147A5064524500 @default.
• W4292560147 hasAuthorship W4292560147A5083419467 @default.
• W4292560147 hasBestOaLocation W42925601471 @default.
• W4292560147 hasConcept C115961682 @default.
• W4292560147 hasConcept C138885662 @default.
• W4292560147 hasConcept C153180895 @default.
• W4292560147 hasConcept C154945302 @default.
• W4292560147 hasConcept C2221639 @default.
• W4292560147 hasConcept C2776401178 @default.
• W4292560147 hasConcept C41008148 @default.
• W4292560147 hasConcept C41895202 @default.
• W4292560147 hasConcept C45347329 @default.
• W4292560147 hasConcept C50644808 @default.
• W4292560147 hasConcept C52622490 @default.
• W4292560147 hasConcept C70437156 @default.
• W4292560147 hasConcept C81363708 @default.
• W4292560147 hasConceptScore W4292560147C115961682 @default.
• W4292560147 hasConceptScore W4292560147C138885662 @default.
• W4292560147 hasConceptScore W4292560147C153180895 @default.
• W4292560147 hasConceptScore W4292560147C154945302 @default.
• W4292560147 hasConceptScore W4292560147C2221639 @default.
• W4292560147 hasConceptScore W4292560147C2776401178 @default.
• W4292560147 hasConceptScore W4292560147C41008148 @default.
• W4292560147 hasConceptScore W4292560147C41895202 @default.
• W4292560147 hasConceptScore W4292560147C45347329 @default.
• W4292560147 hasConceptScore W4292560147C50644808 @default.
• W4292560147 hasConceptScore W4292560147C52622490 @default.
• W4292560147 hasConceptScore W4292560147C70437156 @default.
• W4292560147 hasConceptScore W4292560147C81363708 @default.
• W4292560147 hasLocation W42925601471 @default.
• W4292560147 hasOpenAccess W4292560147 @default.
• W4292560147 hasPrimaryLocation W42925601471 @default.
• W4292560147 hasRelatedWork W2291847203 @default.
• W4292560147 hasRelatedWork W2295021132 @default.
• W4292560147 hasRelatedWork W2319888919 @default.
• W4292560147 hasRelatedWork W2424871898 @default.
• W4292560147 hasRelatedWork W2517027266 @default.
• W4292560147 hasRelatedWork W2546942002 @default.
• W4292560147 hasRelatedWork W3024389224 @default.
• W4292560147 hasRelatedWork W4225850200 @default.
• W4292560147 hasRelatedWork W4367598285 @default.

• next