Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366850930> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4366850930 abstract "Multi-instance multi-label (MIML) learning is widely applicated in numerous domains, such as the image classification where one image contains multiple instances correlated with multiple logic labels simultaneously. The related labels in existing MIML are all assumed as logical labels with equal significance. However, in practical applications in MIML, significance of each label for multiple instances per bag (such as an image) is significant different. Ignoring labeling significance will greatly lose the semantic information of the object, so that MIML is not applicable in complex scenes with a poor learning performance. To this end, this paper proposed a novel MIML framework based on graph label enhancement, namely GLEMIML, to improve the classification performance of MIML by leveraging label significance. GLEMIML first recognizes the correlations among instances by establishing the graph and then migrates the implicit information mined from the feature space to the label space via nonlinear mapping, thus recovering the label significance. Finally, GLEMIML is trained on the enhanced data through matching and interaction mechanisms. GLEMIML (AvgRank: 1.44) can effectively improve the performance of MIML by mining the label distribution mechanism and show better results than the SOTA method (AvgRank: 2.92) on multiple benchmark datasets." @default.
- W4366850930 created "2023-04-25" @default.
- W4366850930 creator A5026348811 @default.
- W4366850930 creator A5035564686 @default.
- W4366850930 creator A5045343174 @default.
- W4366850930 creator A5057256093 @default.
- W4366850930 creator A5063922467 @default.
- W4366850930 creator A5076922237 @default.
- W4366850930 date "2023-04-20" @default.
- W4366850930 modified "2023-10-14" @default.
- W4366850930 title "Graph based Label Enhancement for Multi-instance Multi-label learning" @default.
- W4366850930 doi "https://doi.org/10.48550/arxiv.2304.10705" @default.
- W4366850930 hasPublicationYear "2023" @default.
- W4366850930 type Work @default.
- W4366850930 citedByCount "0" @default.
- W4366850930 crossrefType "posted-content" @default.
- W4366850930 hasAuthorship W4366850930A5026348811 @default.
- W4366850930 hasAuthorship W4366850930A5035564686 @default.
- W4366850930 hasAuthorship W4366850930A5045343174 @default.
- W4366850930 hasAuthorship W4366850930A5057256093 @default.
- W4366850930 hasAuthorship W4366850930A5063922467 @default.
- W4366850930 hasAuthorship W4366850930A5076922237 @default.
- W4366850930 hasBestOaLocation W43668509301 @default.
- W4366850930 hasConcept C105795698 @default.
- W4366850930 hasConcept C119857082 @default.
- W4366850930 hasConcept C132525143 @default.
- W4366850930 hasConcept C13280743 @default.
- W4366850930 hasConcept C153180895 @default.
- W4366850930 hasConcept C154945302 @default.
- W4366850930 hasConcept C165064840 @default.
- W4366850930 hasConcept C185798385 @default.
- W4366850930 hasConcept C205649164 @default.
- W4366850930 hasConcept C33923547 @default.
- W4366850930 hasConcept C41008148 @default.
- W4366850930 hasConcept C80444323 @default.
- W4366850930 hasConcept C83665646 @default.
- W4366850930 hasConceptScore W4366850930C105795698 @default.
- W4366850930 hasConceptScore W4366850930C119857082 @default.
- W4366850930 hasConceptScore W4366850930C132525143 @default.
- W4366850930 hasConceptScore W4366850930C13280743 @default.
- W4366850930 hasConceptScore W4366850930C153180895 @default.
- W4366850930 hasConceptScore W4366850930C154945302 @default.
- W4366850930 hasConceptScore W4366850930C165064840 @default.
- W4366850930 hasConceptScore W4366850930C185798385 @default.
- W4366850930 hasConceptScore W4366850930C205649164 @default.
- W4366850930 hasConceptScore W4366850930C33923547 @default.
- W4366850930 hasConceptScore W4366850930C41008148 @default.
- W4366850930 hasConceptScore W4366850930C80444323 @default.
- W4366850930 hasConceptScore W4366850930C83665646 @default.
- W4366850930 hasLocation W43668509301 @default.
- W4366850930 hasOpenAccess W4366850930 @default.
- W4366850930 hasPrimaryLocation W43668509301 @default.
- W4366850930 hasRelatedWork W1982998847 @default.
- W4366850930 hasRelatedWork W2060018656 @default.
- W4366850930 hasRelatedWork W2090269531 @default.
- W4366850930 hasRelatedWork W2096855366 @default.
- W4366850930 hasRelatedWork W2102298087 @default.
- W4366850930 hasRelatedWork W2167440101 @default.
- W4366850930 hasRelatedWork W2293915134 @default.
- W4366850930 hasRelatedWork W3047965787 @default.
- W4366850930 hasRelatedWork W3108249809 @default.
- W4366850930 hasRelatedWork W3208409104 @default.
- W4366850930 isParatext "false" @default.
- W4366850930 isRetracted "false" @default.
- W4366850930 workType "article" @default.