FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897894800> ?p ?o ?g. }

• W2897894800 endingPage "479" @default.
• W2897894800 startingPage "479" @default.
• W2897894800 abstract "Compared with ordinary image classification tasks, fine-grained image classification is closer to real-life scenes. Its key point is how to find the local areas with sufficient discrimination and perform effective feature learning. Based on a bilinear convolutional neural network (B-CNN), this paper designs a local importance representation convolutional neural network (LIR-CNN) model, which can be divided into three parts. Firstly, the super-pixel segmentation convolution method is used for the input layer of the model. It allows the model to receive images of different sizes and fully considers the complex geometric deformation of the images. Then, we replaced the standard convolution of B-CNN with the proposed local importance representation convolution. It can score each local area of the image using learning to distinguish their importance. Finally, channelwise convolution is proposed and it plays an important role in balancing lightweight network and classification accuracy. Experimental results on the benchmark datasets (e.g., CUB-200-2011, FGVC-Aircraft, and Stanford Cars) showed that the LIR-CNN model had good performance in fine-grained image classification tasks." @default.
• W2897894800 created "2018-10-26" @default.
• W2897894800 creator A5010642871 @default.
• W2897894800 creator A5012164583 @default.
• W2897894800 creator A5071179179 @default.
• W2897894800 date "2018-10-11" @default.
• W2897894800 modified "2023-10-15" @default.
• W2897894800 title "Local Importance Representation Convolutional Neural Network for Fine-Grained Image Classification" @default.
• W2897894800 cites W2064223554 @default.
• W2897894800 cites W2109255472 @default.
• W2897894800 cites W2339876161 @default.
• W2897894800 cites W2549079750 @default.
• W2897894800 cites W2681460984 @default.
• W2897894800 cites W2763070548 @default.
• W2897894800 cites W2765268259 @default.
• W2897894800 cites W2789504340 @default.
• W2897894800 cites W2791437400 @default.
• W2897894800 cites W2796672611 @default.
• W2897894800 cites W2807551730 @default.
• W2897894800 cites W2919115771 @default.
• W2897894800 doi "https://doi.org/10.3390/sym10100479" @default.
• W2897894800 hasPublicationYear "2018" @default.
• W2897894800 type Work @default.
• W2897894800 sameAs 2897894800 @default.
• W2897894800 citedByCount "4" @default.
• W2897894800 countsByYear W28978948002019 @default.
• W2897894800 countsByYear W28978948002020 @default.
• W2897894800 countsByYear W28978948002021 @default.
• W2897894800 crossrefType "journal-article" @default.
• W2897894800 hasAuthorship W2897894800A5010642871 @default.
• W2897894800 hasAuthorship W2897894800A5012164583 @default.
• W2897894800 hasAuthorship W2897894800A5071179179 @default.
• W2897894800 hasBestOaLocation W28978948001 @default.
• W2897894800 hasConcept C108583219 @default.
• W2897894800 hasConcept C115961682 @default.
• W2897894800 hasConcept C13280743 @default.
• W2897894800 hasConcept C138885662 @default.
• W2897894800 hasConcept C153180895 @default.
• W2897894800 hasConcept C154945302 @default.
• W2897894800 hasConcept C17744445 @default.
• W2897894800 hasConcept C185798385 @default.
• W2897894800 hasConcept C199539241 @default.
• W2897894800 hasConcept C205203396 @default.
• W2897894800 hasConcept C205649164 @default.
• W2897894800 hasConcept C26517878 @default.
• W2897894800 hasConcept C2776359362 @default.
• W2897894800 hasConcept C2776401178 @default.
• W2897894800 hasConcept C31972630 @default.
• W2897894800 hasConcept C38652104 @default.
• W2897894800 hasConcept C41008148 @default.
• W2897894800 hasConcept C41895202 @default.
• W2897894800 hasConcept C45347329 @default.
• W2897894800 hasConcept C50644808 @default.
• W2897894800 hasConcept C75294576 @default.
• W2897894800 hasConcept C81363708 @default.
• W2897894800 hasConcept C89600930 @default.
• W2897894800 hasConcept C94625758 @default.
• W2897894800 hasConceptScore W2897894800C108583219 @default.
• W2897894800 hasConceptScore W2897894800C115961682 @default.
• W2897894800 hasConceptScore W2897894800C13280743 @default.
• W2897894800 hasConceptScore W2897894800C138885662 @default.
• W2897894800 hasConceptScore W2897894800C153180895 @default.
• W2897894800 hasConceptScore W2897894800C154945302 @default.
• W2897894800 hasConceptScore W2897894800C17744445 @default.
• W2897894800 hasConceptScore W2897894800C185798385 @default.
• W2897894800 hasConceptScore W2897894800C199539241 @default.
• W2897894800 hasConceptScore W2897894800C205203396 @default.
• W2897894800 hasConceptScore W2897894800C205649164 @default.
• W2897894800 hasConceptScore W2897894800C26517878 @default.
• W2897894800 hasConceptScore W2897894800C2776359362 @default.
• W2897894800 hasConceptScore W2897894800C2776401178 @default.
• W2897894800 hasConceptScore W2897894800C31972630 @default.
• W2897894800 hasConceptScore W2897894800C38652104 @default.
• W2897894800 hasConceptScore W2897894800C41008148 @default.
• W2897894800 hasConceptScore W2897894800C41895202 @default.
• W2897894800 hasConceptScore W2897894800C45347329 @default.
• W2897894800 hasConceptScore W2897894800C50644808 @default.
• W2897894800 hasConceptScore W2897894800C75294576 @default.
• W2897894800 hasConceptScore W2897894800C81363708 @default.
• W2897894800 hasConceptScore W2897894800C89600930 @default.
• W2897894800 hasConceptScore W2897894800C94625758 @default.
• W2897894800 hasFunder F4320321001 @default.
• W2897894800 hasIssue "10" @default.
• W2897894800 hasLocation W28978948001 @default.
• W2897894800 hasLocation W28978948002 @default.
• W2897894800 hasOpenAccess W2897894800 @default.
• W2897894800 hasPrimaryLocation W28978948001 @default.
• W2897894800 hasRelatedWork W2760085659 @default.
• W2897894800 hasRelatedWork W2767708349 @default.
• W2897894800 hasRelatedWork W3013138473 @default.
• W2897894800 hasRelatedWork W3018421652 @default.
• W2897894800 hasRelatedWork W3102253946 @default.
• W2897894800 hasRelatedWork W3144634534 @default.
• W2897894800 hasRelatedWork W3156786002 @default.
• W2897894800 hasRelatedWork W4293211451 @default.
• W2897894800 hasRelatedWork W4312417841 @default.
• W2897894800 hasRelatedWork W564581980 @default.
• W2897894800 hasVolume "10" @default.

• next