Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313331808> ?p ?o ?g. }
- W4313331808 endingPage "16" @default.
- W4313331808 startingPage "1" @default.
- W4313331808 abstract "Multi-label classification aims to recognize multiple objects or attributes from images. The key to solving this issue relies on effectively characterizing the inter-label correlations or dependencies, which bring the prevailing graph neural network. However, current methods often use the co-occurrence probability of labels based on the training set as the adjacency matrix to model this correlation, which is greatly limited by the dataset and affects the model’s generalization ability. This article proposes a Graph Attention Transformer Network, a general framework for multi-label image classification by mining rich and effective label correlation. First, we use the cosine similarity value of the pre-trained label word embedding as the initial correlation matrix, which can represent richer semantic information than the co-occurrence one. Subsequently, we propose the graph attention transformer layer to transfer this adjacency matrix to adapt to the current domain. Our extensive experiments have demonstrated that our proposed methods can achieve highly competitive performance on three datasets." @default.
- W4313331808 created "2023-01-06" @default.
- W4313331808 creator A5002069152 @default.
- W4313331808 creator A5031574929 @default.
- W4313331808 creator A5063145868 @default.
- W4313331808 creator A5063235838 @default.
- W4313331808 creator A5066686240 @default.
- W4313331808 creator A5069383800 @default.
- W4313331808 creator A5074742406 @default.
- W4313331808 date "2023-02-27" @default.
- W4313331808 modified "2023-09-30" @default.
- W4313331808 title "Graph Attention Transformer Network for Multi-label Image Classification" @default.
- W4313331808 cites W1567302070 @default.
- W4313331808 cites W1861492603 @default.
- W4313331808 cites W1999954155 @default.
- W4313331808 cites W2007972815 @default.
- W4313331808 cites W2014421179 @default.
- W4313331808 cites W2021968313 @default.
- W4313331808 cites W2031489346 @default.
- W4313331808 cites W2194775991 @default.
- W4313331808 cites W2250539671 @default.
- W4313331808 cites W2518918709 @default.
- W4313331808 cites W2553156677 @default.
- W4313331808 cites W2792156255 @default.
- W4313331808 cites W2896102499 @default.
- W4313331808 cites W2911286998 @default.
- W4313331808 cites W2962756421 @default.
- W4313331808 cites W2993850790 @default.
- W4313331808 cites W2998420437 @default.
- W4313331808 cites W3031696893 @default.
- W4313331808 cites W3089555680 @default.
- W4313331808 cites W3093048820 @default.
- W4313331808 cites W3104097132 @default.
- W4313331808 cites W3105705953 @default.
- W4313331808 cites W3167456680 @default.
- W4313331808 cites W3213100861 @default.
- W4313331808 cites W3216083537 @default.
- W4313331808 cites W4214931354 @default.
- W4313331808 doi "https://doi.org/10.1145/3578518" @default.
- W4313331808 hasPublicationYear "2023" @default.
- W4313331808 type Work @default.
- W4313331808 citedByCount "1" @default.
- W4313331808 countsByYear W43133318082023 @default.
- W4313331808 crossrefType "journal-article" @default.
- W4313331808 hasAuthorship W4313331808A5002069152 @default.
- W4313331808 hasAuthorship W4313331808A5031574929 @default.
- W4313331808 hasAuthorship W4313331808A5063145868 @default.
- W4313331808 hasAuthorship W4313331808A5063235838 @default.
- W4313331808 hasAuthorship W4313331808A5066686240 @default.
- W4313331808 hasAuthorship W4313331808A5069383800 @default.
- W4313331808 hasAuthorship W4313331808A5074742406 @default.
- W4313331808 hasBestOaLocation W43133318082 @default.
- W4313331808 hasConcept C110484373 @default.
- W4313331808 hasConcept C11413529 @default.
- W4313331808 hasConcept C117220453 @default.
- W4313331808 hasConcept C119857082 @default.
- W4313331808 hasConcept C121332964 @default.
- W4313331808 hasConcept C124101348 @default.
- W4313331808 hasConcept C132525143 @default.
- W4313331808 hasConcept C153180895 @default.
- W4313331808 hasConcept C154945302 @default.
- W4313331808 hasConcept C165801399 @default.
- W4313331808 hasConcept C180356752 @default.
- W4313331808 hasConcept C2524010 @default.
- W4313331808 hasConcept C2780762811 @default.
- W4313331808 hasConcept C2993807640 @default.
- W4313331808 hasConcept C33923547 @default.
- W4313331808 hasConcept C41008148 @default.
- W4313331808 hasConcept C41608201 @default.
- W4313331808 hasConcept C62520636 @default.
- W4313331808 hasConcept C66322947 @default.
- W4313331808 hasConcept C75564084 @default.
- W4313331808 hasConcept C80444323 @default.
- W4313331808 hasConceptScore W4313331808C110484373 @default.
- W4313331808 hasConceptScore W4313331808C11413529 @default.
- W4313331808 hasConceptScore W4313331808C117220453 @default.
- W4313331808 hasConceptScore W4313331808C119857082 @default.
- W4313331808 hasConceptScore W4313331808C121332964 @default.
- W4313331808 hasConceptScore W4313331808C124101348 @default.
- W4313331808 hasConceptScore W4313331808C132525143 @default.
- W4313331808 hasConceptScore W4313331808C153180895 @default.
- W4313331808 hasConceptScore W4313331808C154945302 @default.
- W4313331808 hasConceptScore W4313331808C165801399 @default.
- W4313331808 hasConceptScore W4313331808C180356752 @default.
- W4313331808 hasConceptScore W4313331808C2524010 @default.
- W4313331808 hasConceptScore W4313331808C2780762811 @default.
- W4313331808 hasConceptScore W4313331808C2993807640 @default.
- W4313331808 hasConceptScore W4313331808C33923547 @default.
- W4313331808 hasConceptScore W4313331808C41008148 @default.
- W4313331808 hasConceptScore W4313331808C41608201 @default.
- W4313331808 hasConceptScore W4313331808C62520636 @default.
- W4313331808 hasConceptScore W4313331808C66322947 @default.
- W4313331808 hasConceptScore W4313331808C75564084 @default.
- W4313331808 hasConceptScore W4313331808C80444323 @default.
- W4313331808 hasIssue "4" @default.
- W4313331808 hasLocation W43133318081 @default.
- W4313331808 hasLocation W43133318082 @default.
- W4313331808 hasOpenAccess W4313331808 @default.