Matches in SemOpenAlex for { <https://semopenalex.org/work/W2770178731> ?p ?o ?g. }
- W2770178731 abstract "Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicability is thus limited as the paired data assumption is often violated in practice: many tasks have only a small subset of data available with pairing annotation, or even no paired data at all. In this paper we introduce Deep Matching Autoencoders (DMAE), which learn a common latent space and pairing from unpaired multi-modal data. Specifically we formulate this as a cross-domain representation learning and object matching problem. We simultaneously optimise parameters of representation learning auto-encoders and the pairing of unpaired multi-modal data. This framework elegantly spans the full regime from fully supervised, semi-supervised, and unsupervised (no paired data) multi-modal learning. We show promising results in image captioning, and on a new task that is uniquely enabled by our methodology: unsupervised classifier learning." @default.
- W2770178731 created "2017-12-04" @default.
- W2770178731 creator A5026091793 @default.
- W2770178731 creator A5046358579 @default.
- W2770178731 creator A5087823932 @default.
- W2770178731 date "2017-11-16" @default.
- W2770178731 modified "2023-09-27" @default.
- W2770178731 title "Deep Matching Autoencoders." @default.
- W2770178731 cites W133569503 @default.
- W2770178731 cites W1425104224 @default.
- W2770178731 cites W1511502642 @default.
- W2770178731 cites W1523385540 @default.
- W2770178731 cites W1686810756 @default.
- W2770178731 cites W1861492603 @default.
- W2770178731 cites W1949478088 @default.
- W2770178731 cites W1957706851 @default.
- W2770178731 cites W1964073652 @default.
- W2770178731 cites W2025341678 @default.
- W2770178731 cites W2031648200 @default.
- W2770178731 cites W2046211142 @default.
- W2770178731 cites W205396393 @default.
- W2770178731 cites W2064675550 @default.
- W2770178731 cites W2070753207 @default.
- W2770178731 cites W2100235303 @default.
- W2770178731 cites W2109586012 @default.
- W2770178731 cites W2123024445 @default.
- W2770178731 cites W2124101779 @default.
- W2770178731 cites W2134270519 @default.
- W2770178731 cites W2140406733 @default.
- W2770178731 cites W2141350700 @default.
- W2770178731 cites W2142387771 @default.
- W2770178731 cites W2142900973 @default.
- W2770178731 cites W2184188583 @default.
- W2770178731 cites W2184852195 @default.
- W2770178731 cites W2185175083 @default.
- W2770178731 cites W2294672308 @default.
- W2770178731 cites W2481240925 @default.
- W2770178731 cites W2762484717 @default.
- W2770178731 cites W2949114386 @default.
- W2770178731 cites W2950133940 @default.
- W2770178731 cites W2950616067 @default.
- W2770178731 cites W2952352992 @default.
- W2770178731 cites W3118608800 @default.
- W2770178731 cites W771469340 @default.
- W2770178731 cites W77953724 @default.
- W2770178731 cites W956551720 @default.
- W2770178731 hasPublicationYear "2017" @default.
- W2770178731 type Work @default.
- W2770178731 sameAs 2770178731 @default.
- W2770178731 citedByCount "6" @default.
- W2770178731 countsByYear W27701787312018 @default.
- W2770178731 countsByYear W27701787312019 @default.
- W2770178731 countsByYear W27701787312020 @default.
- W2770178731 countsByYear W27701787312021 @default.
- W2770178731 crossrefType "posted-content" @default.
- W2770178731 hasAuthorship W2770178731A5026091793 @default.
- W2770178731 hasAuthorship W2770178731A5046358579 @default.
- W2770178731 hasAuthorship W2770178731A5087823932 @default.
- W2770178731 hasConcept C101738243 @default.
- W2770178731 hasConcept C105795698 @default.
- W2770178731 hasConcept C108583219 @default.
- W2770178731 hasConcept C119857082 @default.
- W2770178731 hasConcept C121332964 @default.
- W2770178731 hasConcept C14103023 @default.
- W2770178731 hasConcept C144024400 @default.
- W2770178731 hasConcept C153180895 @default.
- W2770178731 hasConcept C154945302 @default.
- W2770178731 hasConcept C165064840 @default.
- W2770178731 hasConcept C17744445 @default.
- W2770178731 hasConcept C199539241 @default.
- W2770178731 hasConcept C2776359362 @default.
- W2770178731 hasConcept C2779903281 @default.
- W2770178731 hasConcept C33923547 @default.
- W2770178731 hasConcept C36289849 @default.
- W2770178731 hasConcept C41008148 @default.
- W2770178731 hasConcept C54101563 @default.
- W2770178731 hasConcept C59404180 @default.
- W2770178731 hasConcept C62520636 @default.
- W2770178731 hasConcept C8038995 @default.
- W2770178731 hasConcept C94625758 @default.
- W2770178731 hasConcept C95623464 @default.
- W2770178731 hasConceptScore W2770178731C101738243 @default.
- W2770178731 hasConceptScore W2770178731C105795698 @default.
- W2770178731 hasConceptScore W2770178731C108583219 @default.
- W2770178731 hasConceptScore W2770178731C119857082 @default.
- W2770178731 hasConceptScore W2770178731C121332964 @default.
- W2770178731 hasConceptScore W2770178731C14103023 @default.
- W2770178731 hasConceptScore W2770178731C144024400 @default.
- W2770178731 hasConceptScore W2770178731C153180895 @default.
- W2770178731 hasConceptScore W2770178731C154945302 @default.
- W2770178731 hasConceptScore W2770178731C165064840 @default.
- W2770178731 hasConceptScore W2770178731C17744445 @default.
- W2770178731 hasConceptScore W2770178731C199539241 @default.
- W2770178731 hasConceptScore W2770178731C2776359362 @default.
- W2770178731 hasConceptScore W2770178731C2779903281 @default.
- W2770178731 hasConceptScore W2770178731C33923547 @default.
- W2770178731 hasConceptScore W2770178731C36289849 @default.
- W2770178731 hasConceptScore W2770178731C41008148 @default.
- W2770178731 hasConceptScore W2770178731C54101563 @default.
- W2770178731 hasConceptScore W2770178731C59404180 @default.