Matches in SemOpenAlex for { <https://semopenalex.org/work/W3107706539> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3107706539 abstract "It is difficult for taste classification of Chinese recipe to achieve satisfactory results based on single-modal data. However, there are few studies on multimodal analysis in this field. In this paper, we put forward to tackle taste classification for Chinese recipe based on image and text fusion algorithms. Firstly, visual features and textual features are extracted from different models, including a convolutional neural network (CNN) constructed for visual feature extraction and a pretrained word2vec model combined with a multi-layer perception network for textual feature extraction. Secondly, two fusion strategies, called feature-level and decision-level fusion, are designed to perform multimodal fusion for the final taste prediction. Several experiments are carried out with K-fold cross-validation to verify the effectiveness of our proposed model. The results show that the multimodal fusion model for taste classification is superior to those based on single-modal features. Besides, compared with feature-level fusion, decision-level fusion performs better in the task of taste classification for Chinese recipe." @default.
- W3107706539 created "2020-12-07" @default.
- W3107706539 creator A5001064887 @default.
- W3107706539 creator A5018908218 @default.
- W3107706539 creator A5028635794 @default.
- W3107706539 date "2020-06-01" @default.
- W3107706539 modified "2023-10-14" @default.
- W3107706539 title "Multimodal Taste Classification of Chinese Recipe Based on Image and Text Fusion" @default.
- W3107706539 cites W1974802615 @default.
- W3107706539 cites W1979008561 @default.
- W3107706539 cites W2057352599 @default.
- W3107706539 cites W2107722796 @default.
- W3107706539 cites W2114315281 @default.
- W3107706539 cites W2130448385 @default.
- W3107706539 cites W2293236424 @default.
- W3107706539 cites W2337233353 @default.
- W3107706539 cites W2526198870 @default.
- W3107706539 cites W2527200148 @default.
- W3107706539 cites W2765401382 @default.
- W3107706539 cites W2923014022 @default.
- W3107706539 cites W3104226648 @default.
- W3107706539 doi "https://doi.org/10.1109/icsgea51094.2020.00050" @default.
- W3107706539 hasPublicationYear "2020" @default.
- W3107706539 type Work @default.
- W3107706539 sameAs 3107706539 @default.
- W3107706539 citedByCount "2" @default.
- W3107706539 countsByYear W31077065392021 @default.
- W3107706539 countsByYear W31077065392023 @default.
- W3107706539 crossrefType "proceedings-article" @default.
- W3107706539 hasAuthorship W3107706539A5001064887 @default.
- W3107706539 hasAuthorship W3107706539A5018908218 @default.
- W3107706539 hasAuthorship W3107706539A5028635794 @default.
- W3107706539 hasConcept C115961682 @default.
- W3107706539 hasConcept C138885662 @default.
- W3107706539 hasConcept C153180895 @default.
- W3107706539 hasConcept C154945302 @default.
- W3107706539 hasConcept C15744967 @default.
- W3107706539 hasConcept C158525013 @default.
- W3107706539 hasConcept C169760540 @default.
- W3107706539 hasConcept C185592680 @default.
- W3107706539 hasConcept C204321447 @default.
- W3107706539 hasConcept C2778671685 @default.
- W3107706539 hasConcept C31903555 @default.
- W3107706539 hasConcept C31972630 @default.
- W3107706539 hasConcept C41008148 @default.
- W3107706539 hasConcept C41895202 @default.
- W3107706539 hasConcept C8868529 @default.
- W3107706539 hasConceptScore W3107706539C115961682 @default.
- W3107706539 hasConceptScore W3107706539C138885662 @default.
- W3107706539 hasConceptScore W3107706539C153180895 @default.
- W3107706539 hasConceptScore W3107706539C154945302 @default.
- W3107706539 hasConceptScore W3107706539C15744967 @default.
- W3107706539 hasConceptScore W3107706539C158525013 @default.
- W3107706539 hasConceptScore W3107706539C169760540 @default.
- W3107706539 hasConceptScore W3107706539C185592680 @default.
- W3107706539 hasConceptScore W3107706539C204321447 @default.
- W3107706539 hasConceptScore W3107706539C2778671685 @default.
- W3107706539 hasConceptScore W3107706539C31903555 @default.
- W3107706539 hasConceptScore W3107706539C31972630 @default.
- W3107706539 hasConceptScore W3107706539C41008148 @default.
- W3107706539 hasConceptScore W3107706539C41895202 @default.
- W3107706539 hasConceptScore W3107706539C8868529 @default.
- W3107706539 hasFunder F4320335777 @default.
- W3107706539 hasLocation W31077065391 @default.
- W3107706539 hasOpenAccess W3107706539 @default.
- W3107706539 hasPrimaryLocation W31077065391 @default.
- W3107706539 hasRelatedWork W2005185696 @default.
- W3107706539 hasRelatedWork W2057200091 @default.
- W3107706539 hasRelatedWork W2092957489 @default.
- W3107706539 hasRelatedWork W2130228941 @default.
- W3107706539 hasRelatedWork W2161229648 @default.
- W3107706539 hasRelatedWork W2235753890 @default.
- W3107706539 hasRelatedWork W2314419244 @default.
- W3107706539 hasRelatedWork W2366116130 @default.
- W3107706539 hasRelatedWork W2993674027 @default.
- W3107706539 hasRelatedWork W3107474891 @default.
- W3107706539 isParatext "false" @default.
- W3107706539 isRetracted "false" @default.
- W3107706539 magId "3107706539" @default.
- W3107706539 workType "article" @default.