FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3185442830> ?p ?o ?g. }

• W3185442830 endingPage "20" @default.
• W3185442830 startingPage "1" @default.
• W3185442830 abstract "Multi-label learning recovers multiple labels from a single instance. It is a more challenging task compared with single-label manner. Most multi-label learning approaches need large-scale well-labeled samples to achieve high accurate performance. However, it is expensive to build such a dataset. In this work, we propose a generic multi-label learning framework based on Adaptive Graph and Marginalized Augmentation (AGMA) in a semi-supervised scenario. Generally speaking, AGMA makes use of a small amount of labeled data associated with a lot of unlabeled data to boost the learning performance. First, an adaptive similarity graph is learned to effectively capture the intrinsic structure within the data. Second, marginalized augmentation strategy is explored to enhance the model generalization and robustness. Third, a feature-label autoencoder is further deployed to improve inferring efficiency. All the modules are jointly trained to benefit each other. State-of-the-art benchmarks in both traditional and zero-shot multi-label learning scenarios are evaluated. Experiments and ablation studies illustrate the accuracy and efficiency of our AGMA method." @default.
• W3185442830 created "2021-08-02" @default.
• W3185442830 creator A5005819096 @default.
• W3185442830 creator A5006924994 @default.
• W3185442830 creator A5083458247 @default.
• W3185442830 date "2021-07-20" @default.
• W3185442830 modified "2023-10-18" @default.
• W3185442830 title "Generic Multi-label Annotation via Adaptive Graph and Marginalized Augmentation" @default.
• W3185442830 cites W1972490990 @default.
• W3185442830 cites W1995282358 @default.
• W3185442830 cites W1998839399 @default.
• W3185442830 cites W2017818587 @default.
• W3185442830 cites W2038967169 @default.
• W3185442830 cites W2042759724 @default.
• W3185442830 cites W2054408796 @default.
• W3185442830 cites W2080063509 @default.
• W3185442830 cites W2088748973 @default.
• W3185442830 cites W2090101874 @default.
• W3185442830 cites W2092887517 @default.
• W3185442830 cites W2097117768 @default.
• W3185442830 cites W2108598243 @default.
• W3185442830 cites W2121407213 @default.
• W3185442830 cites W2128532956 @default.
• W3185442830 cites W2143854982 @default.
• W3185442830 cites W2156935079 @default.
• W3185442830 cites W2198007625 @default.
• W3185442830 cites W2483850719 @default.
• W3185442830 cites W2536305071 @default.
• W3185442830 cites W2584571478 @default.
• W3185442830 cites W2611632661 @default.
• W3185442830 cites W2751774244 @default.
• W3185442830 cites W2761674588 @default.
• W3185442830 cites W2783863635 @default.
• W3185442830 cites W2790640759 @default.
• W3185442830 cites W2799787995 @default.
• W3185442830 cites W2889731794 @default.
• W3185442830 cites W2893830906 @default.
• W3185442830 cites W2904251885 @default.
• W3185442830 cites W2904965361 @default.
• W3185442830 cites W2942759156 @default.
• W3185442830 cites W2987491803 @default.
• W3185442830 cites W2990654629 @default.
• W3185442830 cites W2997770686 @default.
• W3185442830 cites W3143107425 @default.
• W3185442830 cites W4292363360 @default.
• W3185442830 cites W66588809 @default.
• W3185442830 doi "https://doi.org/10.1145/3451884" @default.
• W3185442830 hasPublicationYear "2021" @default.
• W3185442830 type Work @default.
• W3185442830 sameAs 3185442830 @default.
• W3185442830 citedByCount "3" @default.
• W3185442830 countsByYear W31854428302021 @default.
• W3185442830 countsByYear W31854428302022 @default.
• W3185442830 countsByYear W31854428302023 @default.
• W3185442830 crossrefType "journal-article" @default.
• W3185442830 hasAuthorship W3185442830A5005819096 @default.
• W3185442830 hasAuthorship W3185442830A5006924994 @default.
• W3185442830 hasAuthorship W3185442830A5083458247 @default.
• W3185442830 hasConcept C101738243 @default.
• W3185442830 hasConcept C104317684 @default.
• W3185442830 hasConcept C108583219 @default.
• W3185442830 hasConcept C119857082 @default.
• W3185442830 hasConcept C124101348 @default.
• W3185442830 hasConcept C132525143 @default.
• W3185442830 hasConcept C153180895 @default.
• W3185442830 hasConcept C154945302 @default.
• W3185442830 hasConcept C185592680 @default.
• W3185442830 hasConcept C41008148 @default.
• W3185442830 hasConcept C55493867 @default.
• W3185442830 hasConcept C63479239 @default.
• W3185442830 hasConcept C80444323 @default.
• W3185442830 hasConceptScore W3185442830C101738243 @default.
• W3185442830 hasConceptScore W3185442830C104317684 @default.
• W3185442830 hasConceptScore W3185442830C108583219 @default.
• W3185442830 hasConceptScore W3185442830C119857082 @default.
• W3185442830 hasConceptScore W3185442830C124101348 @default.
• W3185442830 hasConceptScore W3185442830C132525143 @default.
• W3185442830 hasConceptScore W3185442830C153180895 @default.
• W3185442830 hasConceptScore W3185442830C154945302 @default.
• W3185442830 hasConceptScore W3185442830C185592680 @default.
• W3185442830 hasConceptScore W3185442830C41008148 @default.
• W3185442830 hasConceptScore W3185442830C55493867 @default.
• W3185442830 hasConceptScore W3185442830C63479239 @default.
• W3185442830 hasConceptScore W3185442830C80444323 @default.
• W3185442830 hasIssue "1" @default.
• W3185442830 hasLocation W31854428301 @default.
• W3185442830 hasOpenAccess W3185442830 @default.
• W3185442830 hasPrimaryLocation W31854428301 @default.
• W3185442830 hasRelatedWork W2159052453 @default.
• W3185442830 hasRelatedWork W2566616303 @default.
• W3185442830 hasRelatedWork W2734887215 @default.
• W3185442830 hasRelatedWork W2752972570 @default.
• W3185442830 hasRelatedWork W2803255133 @default.
• W3185442830 hasRelatedWork W2891286602 @default.
• W3185442830 hasRelatedWork W2909431601 @default.
• W3185442830 hasRelatedWork W3013693939 @default.
• W3185442830 hasRelatedWork W3131327266 @default.
• W3185442830 hasRelatedWork W4297051394 @default.

• next