Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035356442> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3035356442 abstract "Low-rank representation is powerful for recover-ing and clustering the subspace structures, but it cannot obtain deep hierarchical information due to the single-layer mode. In this paper, we present a new and effective strategy to extend the sin-gle-layer latent low-rank models into multi-ple-layers, and propose a new and progressive Deep Latent Low-Rank Fusion Network (DLRF-Net) to uncover deep features and struc-tures embedded in input data. The basic idea of DLRF-Net is to refine features progressively from the previous layers by fusing the subspaces in each layer, which can potentially obtain accurate fea-tures and subspaces for representation. To learn deep information, DLRF-Net inputs shallow fea-tures of the last layers into subsequent layers. Then, it recovers the deeper features and hierar-chical information by congregating the projective subspaces and clustering subspaces respectively in each layer. Thus, one can learn hierarchical sub-spaces, remove noise and discover the underlying clean subspaces. Note that most existing latent low-rank coding models can be extended to multi-layers using DLRF-Net. Extensive results show that our network can deliver enhanced perfor-mance over other related frameworks." @default.
- W3035356442 created "2020-06-19" @default.
- W3035356442 creator A5019542310 @default.
- W3035356442 creator A5065361552 @default.
- W3035356442 creator A5088888083 @default.
- W3035356442 creator A5091734811 @default.
- W3035356442 date "2020-07-01" @default.
- W3035356442 modified "2023-10-16" @default.
- W3035356442 title "Deep Latent Low-Rank Fusion Network for Progressive Subspace Discovery" @default.
- W3035356442 doi "https://doi.org/10.24963/ijcai.2020/383" @default.
- W3035356442 hasPublicationYear "2020" @default.
- W3035356442 type Work @default.
- W3035356442 sameAs 3035356442 @default.
- W3035356442 citedByCount "11" @default.
- W3035356442 countsByYear W30353564422020 @default.
- W3035356442 countsByYear W30353564422021 @default.
- W3035356442 countsByYear W30353564422022 @default.
- W3035356442 countsByYear W30353564422023 @default.
- W3035356442 crossrefType "proceedings-article" @default.
- W3035356442 hasAuthorship W3035356442A5019542310 @default.
- W3035356442 hasAuthorship W3035356442A5065361552 @default.
- W3035356442 hasAuthorship W3035356442A5088888083 @default.
- W3035356442 hasAuthorship W3035356442A5091734811 @default.
- W3035356442 hasBestOaLocation W30353564421 @default.
- W3035356442 hasConcept C114614502 @default.
- W3035356442 hasConcept C12362212 @default.
- W3035356442 hasConcept C124101348 @default.
- W3035356442 hasConcept C153180895 @default.
- W3035356442 hasConcept C154945302 @default.
- W3035356442 hasConcept C164226766 @default.
- W3035356442 hasConcept C17744445 @default.
- W3035356442 hasConcept C199539241 @default.
- W3035356442 hasConcept C2524010 @default.
- W3035356442 hasConcept C2776359362 @default.
- W3035356442 hasConcept C32834561 @default.
- W3035356442 hasConcept C33923547 @default.
- W3035356442 hasConcept C41008148 @default.
- W3035356442 hasConcept C73555534 @default.
- W3035356442 hasConcept C94625758 @default.
- W3035356442 hasConceptScore W3035356442C114614502 @default.
- W3035356442 hasConceptScore W3035356442C12362212 @default.
- W3035356442 hasConceptScore W3035356442C124101348 @default.
- W3035356442 hasConceptScore W3035356442C153180895 @default.
- W3035356442 hasConceptScore W3035356442C154945302 @default.
- W3035356442 hasConceptScore W3035356442C164226766 @default.
- W3035356442 hasConceptScore W3035356442C17744445 @default.
- W3035356442 hasConceptScore W3035356442C199539241 @default.
- W3035356442 hasConceptScore W3035356442C2524010 @default.
- W3035356442 hasConceptScore W3035356442C2776359362 @default.
- W3035356442 hasConceptScore W3035356442C32834561 @default.
- W3035356442 hasConceptScore W3035356442C33923547 @default.
- W3035356442 hasConceptScore W3035356442C41008148 @default.
- W3035356442 hasConceptScore W3035356442C73555534 @default.
- W3035356442 hasConceptScore W3035356442C94625758 @default.
- W3035356442 hasLocation W30353564421 @default.
- W3035356442 hasOpenAccess W3035356442 @default.
- W3035356442 hasPrimaryLocation W30353564421 @default.
- W3035356442 hasRelatedWork W1653012935 @default.
- W3035356442 hasRelatedWork W2065962751 @default.
- W3035356442 hasRelatedWork W2066106635 @default.
- W3035356442 hasRelatedWork W2069324581 @default.
- W3035356442 hasRelatedWork W2121787161 @default.
- W3035356442 hasRelatedWork W2380748039 @default.
- W3035356442 hasRelatedWork W2766855804 @default.
- W3035356442 hasRelatedWork W2950200016 @default.
- W3035356442 hasRelatedWork W2968452750 @default.
- W3035356442 hasRelatedWork W4300495377 @default.
- W3035356442 isParatext "false" @default.
- W3035356442 isRetracted "false" @default.
- W3035356442 magId "3035356442" @default.
- W3035356442 workType "article" @default.