FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385380820> ?p ?o ?g. }

• W4385380820 endingPage "329" @default.
• W4385380820 startingPage "313" @default.
• W4385380820 abstract "As a new pre-training paradigm, masked autoencoding has significantly advanced self-supervised learning in NLP and computer vision. However, it remains under exploration whether masked autoencoding can be generalized to feature learning in point clouds. In this paper, we present a novel self-supervised learning framework based on Joint Masked Autoencoding with global reconstruction (JMA). The key idea is to randomly mask some patches in the point clouds and use the visible patches to reconstruct the masked ones. In contrast with previous methods based on masked autoencoding, our JMA splits the point clouds into multiple partitions and uses every single partition to predict all other partitions, which involves simultaneous learning of multiple masked autoencoding tasks. Moreover, each partition is supervised to learn the global shape of the point clouds, which enables the model to capture global pictures of the original point clouds. Extensive results demonstrate the advantages of the proposed method on various downstream tasks. Specifically, on the widely used ModelNet40 and the more challenging ScanObjectNN datasets, the pre-trained model achieves consistently improved performances." @default.
• W4385380820 created "2023-07-30" @default.
• W4385380820 creator A5005513706 @default.
• W4385380820 date "2023-01-01" @default.
• W4385380820 modified "2023-09-27" @default.
• W4385380820 title "Joint Masked Autoencoding with Global Reconstruction for Point Cloud Learning" @default.
• W4385380820 cites W1644641054 @default.
• W4385380820 cites W2041642242 @default.
• W4385380820 cites W2560722161 @default.
• W4385380820 cites W2796426482 @default.
• W4385380820 cites W2850910281 @default.
• W4385380820 cites W2963231572 @default.
• W4385380820 cites W2963281829 @default.
• W4385380820 cites W2963443993 @default.
• W4385380820 cites W2963680240 @default.
• W4385380820 cites W2963719584 @default.
• W4385380820 cites W2964228567 @default.
• W4385380820 cites W2970641574 @default.
• W4385380820 cites W2979548969 @default.
• W4385380820 cites W2979750740 @default.
• W4385380820 cites W2981440248 @default.
• W4385380820 cites W2985088149 @default.
• W4385380820 cites W2988715931 @default.
• W4385380820 cites W3008681464 @default.
• W4385380820 cites W3009750677 @default.
• W4385380820 cites W3011411500 @default.
• W4385380820 cites W3018902719 @default.
• W4385380820 cites W3034314779 @default.
• W4385380820 cites W3034459762 @default.
• W4385380820 cites W3035172746 @default.
• W4385380820 cites W3035524453 @default.
• W4385380820 cites W3035574168 @default.
• W4385380820 cites W3035729912 @default.
• W4385380820 cites W3046614818 @default.
• W4385380820 cites W3109944402 @default.
• W4385380820 cites W3118806719 @default.
• W4385380820 cites W3119708198 @default.
• W4385380820 cites W3128716822 @default.
• W4385380820 cites W3153465022 @default.
• W4385380820 cites W3155390614 @default.
• W4385380820 cites W3189347889 @default.
• W4385380820 cites W3197097949 @default.
• W4385380820 cites W3202611145 @default.
• W4385380820 cites W3211461682 @default.
• W4385380820 cites W4214526701 @default.
• W4385380820 cites W4214755140 @default.
• W4385380820 cites W4293704629 @default.
• W4385380820 cites W4312270234 @default.
• W4385380820 cites W4312317653 @default.
• W4385380820 cites W4312804044 @default.
• W4385380820 cites W4313156423 @default.
• W4385380820 cites W4372053342 @default.
• W4385380820 doi "https://doi.org/10.1007/978-3-031-37660-3_22" @default.
• W4385380820 hasPublicationYear "2023" @default.
• W4385380820 type Work @default.
• W4385380820 citedByCount "0" @default.
• W4385380820 crossrefType "book-chapter" @default.
• W4385380820 hasAuthorship W4385380820A5005513706 @default.
• W4385380820 hasConcept C114614502 @default.
• W4385380820 hasConcept C119857082 @default.
• W4385380820 hasConcept C127413603 @default.
• W4385380820 hasConcept C131979681 @default.
• W4385380820 hasConcept C138885662 @default.
• W4385380820 hasConcept C153180895 @default.
• W4385380820 hasConcept C154945302 @default.
• W4385380820 hasConcept C170154142 @default.
• W4385380820 hasConcept C18555067 @default.
• W4385380820 hasConcept C2524010 @default.
• W4385380820 hasConcept C26517878 @default.
• W4385380820 hasConcept C2776401178 @default.
• W4385380820 hasConcept C28719098 @default.
• W4385380820 hasConcept C33923547 @default.
• W4385380820 hasConcept C38652104 @default.
• W4385380820 hasConcept C41008148 @default.
• W4385380820 hasConcept C41895202 @default.
• W4385380820 hasConcept C42812 @default.
• W4385380820 hasConceptScore W4385380820C114614502 @default.
• W4385380820 hasConceptScore W4385380820C119857082 @default.
• W4385380820 hasConceptScore W4385380820C127413603 @default.
• W4385380820 hasConceptScore W4385380820C131979681 @default.
• W4385380820 hasConceptScore W4385380820C138885662 @default.
• W4385380820 hasConceptScore W4385380820C153180895 @default.
• W4385380820 hasConceptScore W4385380820C154945302 @default.
• W4385380820 hasConceptScore W4385380820C170154142 @default.
• W4385380820 hasConceptScore W4385380820C18555067 @default.
• W4385380820 hasConceptScore W4385380820C2524010 @default.
• W4385380820 hasConceptScore W4385380820C26517878 @default.
• W4385380820 hasConceptScore W4385380820C2776401178 @default.
• W4385380820 hasConceptScore W4385380820C28719098 @default.
• W4385380820 hasConceptScore W4385380820C33923547 @default.
• W4385380820 hasConceptScore W4385380820C38652104 @default.
• W4385380820 hasConceptScore W4385380820C41008148 @default.
• W4385380820 hasConceptScore W4385380820C41895202 @default.
• W4385380820 hasConceptScore W4385380820C42812 @default.
• W4385380820 hasLocation W43853808201 @default.
• W4385380820 hasOpenAccess W4385380820 @default.
• W4385380820 hasPrimaryLocation W43853808201 @default.
• W4385380820 hasRelatedWork W1120630214 @default.

• next