Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200159660> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3200159660 abstract "When applying machine learning to tackle realworld problems, it is common to see that objects come with multiple labels rather than a single label. In addition, complex objects can be composed of multiple modalities, e.g. a post on social media may contain both texts and images. Previous approaches typically treat every modality as a whole, while it is not the case in real world, as every post may contain multiple images and texts with quite diverse semantic meanings. Therefore, Multi-modal Multi-instance Multi-label (M3) learning was proposed. Previous attempt at M3 learning argues that exploiting label correlations is crucial. In this paper, we find that we can handle M3 problems using graph convolutional network. Specifically, a graph is built over all labels and each label is initially represented by its word embedding. The main goal for GCN is to map those label embed dings into inter-correlated label classifiers. Moreover, multi-instance aggregation is based on attention mechanism, making it more interpretable because it naturally learns to discover which pattern triggers the labels. Empirical studies are conducted on both benchmark datasets and industrial datasets, validating the effectiveness of our method, and it is demonstrated in ablation studies that the components in our methods are essential." @default.
- W3200159660 created "2021-09-27" @default.
- W3200159660 creator A5046597133 @default.
- W3200159660 creator A5073912249 @default.
- W3200159660 creator A5076690074 @default.
- W3200159660 date "2021-07-18" @default.
- W3200159660 modified "2023-09-28" @default.
- W3200159660 title "Multi-Modal Multi-Instance Multi-Label Learning with Graph Convolutional Network" @default.
- W3200159660 cites W1900086069 @default.
- W3200159660 cites W1996462768 @default.
- W3200159660 cites W1999954155 @default.
- W3200159660 cites W2047221353 @default.
- W3200159660 cites W2079221635 @default.
- W3200159660 cites W2121625657 @default.
- W3200159660 cites W2133288557 @default.
- W3200159660 cites W2134604967 @default.
- W3200159660 cites W2156935079 @default.
- W3200159660 cites W2584931758 @default.
- W3200159660 cites W2808958151 @default.
- W3200159660 cites W2932399282 @default.
- W3200159660 doi "https://doi.org/10.1109/ijcnn52387.2021.9534428" @default.
- W3200159660 hasPublicationYear "2021" @default.
- W3200159660 type Work @default.
- W3200159660 sameAs 3200159660 @default.
- W3200159660 citedByCount "2" @default.
- W3200159660 countsByYear W32001596602022 @default.
- W3200159660 countsByYear W32001596602023 @default.
- W3200159660 crossrefType "proceedings-article" @default.
- W3200159660 hasAuthorship W3200159660A5046597133 @default.
- W3200159660 hasAuthorship W3200159660A5073912249 @default.
- W3200159660 hasAuthorship W3200159660A5076690074 @default.
- W3200159660 hasConcept C119857082 @default.
- W3200159660 hasConcept C132525143 @default.
- W3200159660 hasConcept C13280743 @default.
- W3200159660 hasConcept C153180895 @default.
- W3200159660 hasConcept C154945302 @default.
- W3200159660 hasConcept C185592680 @default.
- W3200159660 hasConcept C185798385 @default.
- W3200159660 hasConcept C188027245 @default.
- W3200159660 hasConcept C205649164 @default.
- W3200159660 hasConcept C41008148 @default.
- W3200159660 hasConcept C41608201 @default.
- W3200159660 hasConcept C71139939 @default.
- W3200159660 hasConcept C80444323 @default.
- W3200159660 hasConceptScore W3200159660C119857082 @default.
- W3200159660 hasConceptScore W3200159660C132525143 @default.
- W3200159660 hasConceptScore W3200159660C13280743 @default.
- W3200159660 hasConceptScore W3200159660C153180895 @default.
- W3200159660 hasConceptScore W3200159660C154945302 @default.
- W3200159660 hasConceptScore W3200159660C185592680 @default.
- W3200159660 hasConceptScore W3200159660C185798385 @default.
- W3200159660 hasConceptScore W3200159660C188027245 @default.
- W3200159660 hasConceptScore W3200159660C205649164 @default.
- W3200159660 hasConceptScore W3200159660C41008148 @default.
- W3200159660 hasConceptScore W3200159660C41608201 @default.
- W3200159660 hasConceptScore W3200159660C71139939 @default.
- W3200159660 hasConceptScore W3200159660C80444323 @default.
- W3200159660 hasLocation W32001596601 @default.
- W3200159660 hasOpenAccess W3200159660 @default.
- W3200159660 hasPrimaryLocation W32001596601 @default.
- W3200159660 hasRelatedWork W112744582 @default.
- W3200159660 hasRelatedWork W1485630101 @default.
- W3200159660 hasRelatedWork W172869079 @default.
- W3200159660 hasRelatedWork W2498017833 @default.
- W3200159660 hasRelatedWork W2798513620 @default.
- W3200159660 hasRelatedWork W2961085424 @default.
- W3200159660 hasRelatedWork W4298130664 @default.
- W3200159660 hasRelatedWork W4299906651 @default.
- W3200159660 hasRelatedWork W4306674287 @default.
- W3200159660 hasRelatedWork W4224009465 @default.
- W3200159660 isParatext "false" @default.
- W3200159660 isRetracted "false" @default.
- W3200159660 magId "3200159660" @default.
- W3200159660 workType "article" @default.