Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136209729> ?p ?o ?g. }
- W3136209729 endingPage "2136" @default.
- W3136209729 startingPage "2136" @default.
- W3136209729 abstract "Sharing our feelings through content with images and short videos is one main way of expression on social networks. Visual content can affect people’s emotions, which makes the task of analyzing the sentimental information of visual content more and more concerned. Most of the current methods focus on how to improve the local emotional representations to get better performance of sentiment analysis and ignore the problem of how to perceive objects of different scales and different emotional intensity in complex scenes. In this paper, based on the alterable scale and multi-level local regional emotional affinity analysis under the global perspective, we propose a multi-level context pyramid network (MCPNet) for visual sentiment analysis by combining local and global representations to improve the classification performance. Firstly, Resnet101 is employed as backbone to obtain multi-level emotional representation representing different degrees of semantic information and detailed information. Next, the multi-scale adaptive context modules (MACM) are proposed to learn the sentiment correlation degree of different regions for different scale in the image, and to extract the multi-scale context features for each level deep representation. Finally, different levels of context features are combined to obtain the multi-cue sentimental feature for image sentiment classification. Extensive experimental results on seven commonly used visual sentiment datasets illustrate that our method outperforms the state-of-the-art methods, especially the accuracy on the FI dataset exceeds 90%." @default.
- W3136209729 created "2021-03-29" @default.
- W3136209729 creator A5007354180 @default.
- W3136209729 creator A5020477257 @default.
- W3136209729 creator A5052471212 @default.
- W3136209729 creator A5053820185 @default.
- W3136209729 date "2021-03-18" @default.
- W3136209729 modified "2023-10-06" @default.
- W3136209729 title "Multi-Level Context Pyramid Network for Visual Sentiment Analysis" @default.
- W3136209729 cites W2063948594 @default.
- W3136209729 cites W2118526556 @default.
- W3136209729 cites W2121947860 @default.
- W3136209729 cites W2125387256 @default.
- W3136209729 cites W2552066052 @default.
- W3136209729 cites W2570829410 @default.
- W3136209729 cites W2618530766 @default.
- W3136209729 cites W2793857798 @default.
- W3136209729 cites W2805121932 @default.
- W3136209729 cites W2896767769 @default.
- W3136209729 cites W2908347420 @default.
- W3136209729 cites W2935600691 @default.
- W3136209729 cites W2963464104 @default.
- W3136209729 cites W3003362227 @default.
- W3136209729 cites W3032532364 @default.
- W3136209729 cites W639708223 @default.
- W3136209729 doi "https://doi.org/10.3390/s21062136" @default.
- W3136209729 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8003296" @default.
- W3136209729 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33803744" @default.
- W3136209729 hasPublicationYear "2021" @default.
- W3136209729 type Work @default.
- W3136209729 sameAs 3136209729 @default.
- W3136209729 citedByCount "6" @default.
- W3136209729 countsByYear W31362097292022 @default.
- W3136209729 countsByYear W31362097292023 @default.
- W3136209729 crossrefType "journal-article" @default.
- W3136209729 hasAuthorship W3136209729A5007354180 @default.
- W3136209729 hasAuthorship W3136209729A5020477257 @default.
- W3136209729 hasAuthorship W3136209729A5052471212 @default.
- W3136209729 hasAuthorship W3136209729A5053820185 @default.
- W3136209729 hasBestOaLocation W31362097291 @default.
- W3136209729 hasConcept C120665830 @default.
- W3136209729 hasConcept C121332964 @default.
- W3136209729 hasConcept C12713177 @default.
- W3136209729 hasConcept C138885662 @default.
- W3136209729 hasConcept C142575187 @default.
- W3136209729 hasConcept C151730666 @default.
- W3136209729 hasConcept C153180895 @default.
- W3136209729 hasConcept C154945302 @default.
- W3136209729 hasConcept C17744445 @default.
- W3136209729 hasConcept C192209626 @default.
- W3136209729 hasConcept C199539241 @default.
- W3136209729 hasConcept C204321447 @default.
- W3136209729 hasConcept C2524010 @default.
- W3136209729 hasConcept C2776359362 @default.
- W3136209729 hasConcept C2776401178 @default.
- W3136209729 hasConcept C2778755073 @default.
- W3136209729 hasConcept C2779343474 @default.
- W3136209729 hasConcept C33923547 @default.
- W3136209729 hasConcept C41008148 @default.
- W3136209729 hasConcept C41895202 @default.
- W3136209729 hasConcept C62520636 @default.
- W3136209729 hasConcept C64754055 @default.
- W3136209729 hasConcept C66402592 @default.
- W3136209729 hasConcept C86803240 @default.
- W3136209729 hasConcept C94625758 @default.
- W3136209729 hasConceptScore W3136209729C120665830 @default.
- W3136209729 hasConceptScore W3136209729C121332964 @default.
- W3136209729 hasConceptScore W3136209729C12713177 @default.
- W3136209729 hasConceptScore W3136209729C138885662 @default.
- W3136209729 hasConceptScore W3136209729C142575187 @default.
- W3136209729 hasConceptScore W3136209729C151730666 @default.
- W3136209729 hasConceptScore W3136209729C153180895 @default.
- W3136209729 hasConceptScore W3136209729C154945302 @default.
- W3136209729 hasConceptScore W3136209729C17744445 @default.
- W3136209729 hasConceptScore W3136209729C192209626 @default.
- W3136209729 hasConceptScore W3136209729C199539241 @default.
- W3136209729 hasConceptScore W3136209729C204321447 @default.
- W3136209729 hasConceptScore W3136209729C2524010 @default.
- W3136209729 hasConceptScore W3136209729C2776359362 @default.
- W3136209729 hasConceptScore W3136209729C2776401178 @default.
- W3136209729 hasConceptScore W3136209729C2778755073 @default.
- W3136209729 hasConceptScore W3136209729C2779343474 @default.
- W3136209729 hasConceptScore W3136209729C33923547 @default.
- W3136209729 hasConceptScore W3136209729C41008148 @default.
- W3136209729 hasConceptScore W3136209729C41895202 @default.
- W3136209729 hasConceptScore W3136209729C62520636 @default.
- W3136209729 hasConceptScore W3136209729C64754055 @default.
- W3136209729 hasConceptScore W3136209729C66402592 @default.
- W3136209729 hasConceptScore W3136209729C86803240 @default.
- W3136209729 hasConceptScore W3136209729C94625758 @default.
- W3136209729 hasFunder F4320321001 @default.
- W3136209729 hasFunder F4320321921 @default.
- W3136209729 hasFunder F4320335787 @default.
- W3136209729 hasIssue "6" @default.
- W3136209729 hasLocation W31362097291 @default.
- W3136209729 hasLocation W31362097292 @default.
- W3136209729 hasOpenAccess W3136209729 @default.
- W3136209729 hasPrimaryLocation W31362097291 @default.