Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362015145> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4362015145 endingPage "4291" @default.
- W4362015145 startingPage "4273" @default.
- W4362015145 abstract "The image emotion classification task aims to use the model to automatically predict the emotional response of people when they see the image. Studies have shown that certain local regions are more likely to inspire an emotional response than the whole image. However, existing methods perform poorly in predicting the details of emotional regions and are prone to overfitting during training due to the small size of the dataset. Therefore, this study proposes an image emotion classification network based on multilayer attentional interaction and adaptive feature aggregation. To perform more accurate emotional region prediction, this study designs a multilayer attentional interaction module. The module calculates spatial attention maps for higher-layer semantic features and fusion features through a multilayer shuffle attention module. Through layer-by-layer up-sampling and gating operations, the higher-layer features guide the lower-layer features to learn, eventually achieving sentiment region prediction at the optimal scale. To complement the important information lost by layer-by-layer fusion, this study not only adds an intra-layer fusion to the multilayer attention interaction module but also designs an adaptive feature aggregation module. The module uses global average pooling to compress spatial information and connect channel information from all layers. Then, the module adaptively generates a set of aggregated weights through two fully connected layers to augment the original features of each layer. Eventually, the semantics and details of the different layers are aggregated through gating operations and residual connectivity to complement the lost information. To reduce overfitting on small datasets, the network is pre-trained on the FI dataset, and further weight fine-tuning is performed on the small dataset. The experimental results on the FI, Twitter I and Emotion ROI (Region of Interest) datasets show that the proposed network exceeds existing image emotion classification methods, with accuracies of 90.27%, 84.66% and 84.96%." @default.
- W4362015145 created "2023-04-05" @default.
- W4362015145 creator A5029366957 @default.
- W4362015145 creator A5044207716 @default.
- W4362015145 creator A5068392152 @default.
- W4362015145 creator A5084629039 @default.
- W4362015145 date "2023-01-01" @default.
- W4362015145 modified "2023-10-11" @default.
- W4362015145 title "Image Emotion Classification Network Based on Multilayer Attentional Interaction, Adaptive Feature Aggregation" @default.
- W4362015145 doi "https://doi.org/10.32604/cmc.2023.036975" @default.
- W4362015145 hasPublicationYear "2023" @default.
- W4362015145 type Work @default.
- W4362015145 citedByCount "0" @default.
- W4362015145 crossrefType "journal-article" @default.
- W4362015145 hasAuthorship W4362015145A5029366957 @default.
- W4362015145 hasAuthorship W4362015145A5044207716 @default.
- W4362015145 hasAuthorship W4362015145A5068392152 @default.
- W4362015145 hasAuthorship W4362015145A5084629039 @default.
- W4362015145 hasBestOaLocation W43620151451 @default.
- W4362015145 hasConcept C104317684 @default.
- W4362015145 hasConcept C112313634 @default.
- W4362015145 hasConcept C127716648 @default.
- W4362015145 hasConcept C138885662 @default.
- W4362015145 hasConcept C153180895 @default.
- W4362015145 hasConcept C154945302 @default.
- W4362015145 hasConcept C177264268 @default.
- W4362015145 hasConcept C178790620 @default.
- W4362015145 hasConcept C185592680 @default.
- W4362015145 hasConcept C188082640 @default.
- W4362015145 hasConcept C199360897 @default.
- W4362015145 hasConcept C22019652 @default.
- W4362015145 hasConcept C2776401178 @default.
- W4362015145 hasConcept C2779227376 @default.
- W4362015145 hasConcept C41008148 @default.
- W4362015145 hasConcept C41895202 @default.
- W4362015145 hasConcept C50644808 @default.
- W4362015145 hasConcept C55493867 @default.
- W4362015145 hasConcept C70437156 @default.
- W4362015145 hasConceptScore W4362015145C104317684 @default.
- W4362015145 hasConceptScore W4362015145C112313634 @default.
- W4362015145 hasConceptScore W4362015145C127716648 @default.
- W4362015145 hasConceptScore W4362015145C138885662 @default.
- W4362015145 hasConceptScore W4362015145C153180895 @default.
- W4362015145 hasConceptScore W4362015145C154945302 @default.
- W4362015145 hasConceptScore W4362015145C177264268 @default.
- W4362015145 hasConceptScore W4362015145C178790620 @default.
- W4362015145 hasConceptScore W4362015145C185592680 @default.
- W4362015145 hasConceptScore W4362015145C188082640 @default.
- W4362015145 hasConceptScore W4362015145C199360897 @default.
- W4362015145 hasConceptScore W4362015145C22019652 @default.
- W4362015145 hasConceptScore W4362015145C2776401178 @default.
- W4362015145 hasConceptScore W4362015145C2779227376 @default.
- W4362015145 hasConceptScore W4362015145C41008148 @default.
- W4362015145 hasConceptScore W4362015145C41895202 @default.
- W4362015145 hasConceptScore W4362015145C50644808 @default.
- W4362015145 hasConceptScore W4362015145C55493867 @default.
- W4362015145 hasConceptScore W4362015145C70437156 @default.
- W4362015145 hasIssue "2" @default.
- W4362015145 hasLocation W43620151451 @default.
- W4362015145 hasOpenAccess W4362015145 @default.
- W4362015145 hasPrimaryLocation W43620151451 @default.
- W4362015145 hasRelatedWork W2375904069 @default.
- W4362015145 hasRelatedWork W2944724518 @default.
- W4362015145 hasRelatedWork W2944843851 @default.
- W4362015145 hasRelatedWork W2951391129 @default.
- W4362015145 hasRelatedWork W3126373388 @default.
- W4362015145 hasRelatedWork W3202244193 @default.
- W4362015145 hasRelatedWork W3206592002 @default.
- W4362015145 hasRelatedWork W4225691219 @default.
- W4362015145 hasRelatedWork W4281640556 @default.
- W4362015145 hasRelatedWork W785854688 @default.
- W4362015145 hasVolume "75" @default.
- W4362015145 isParatext "false" @default.
- W4362015145 isRetracted "false" @default.
- W4362015145 workType "article" @default.