FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894544906> ?p ?o ?g. }

• W2894544906 endingPage "867" @default.
• W2894544906 startingPage "853" @default.
• W2894544906 abstract "Domain-invariant (view-invariant and modality-invariant) feature representation is essential for human action recognition. Moreover, given a discriminative visual representation, it is critical to discover the latent correlations among multiple actions in order to facilitate action modeling. To address these problems, we propose a multi-domain and multi-task learning (MDMTL) method to: 1) extract domain-invariant information for multi-view and multi-modal action representation and 2) explore the relatedness among multiple action categories. Specifically, we present a sparse transfer learning-based method to co-embed multi-domain (multi-view and multi-modality) data into a single common space for discriminative feature learning. Additionally, visual feature learning is incorporated into the multi-task learning framework, with the Frobenius-norm regularization term and the sparse constraint term, for joint task modeling and task relatedness-induced feature learning. To the best of our knowledge, MDMTL is the first supervised framework to jointly realize domain-invariant feature learning and task modeling for multi-domain action recognition. Experiments conducted on the INRIA Xmas Motion Acquisition Sequences data set, the MSR Daily Activity 3D (DailyActivity3D) data set, and the Multi-modal & Multi-view & Interactive data set, which is the most recent and largest multi-view and multi-model action recognition data set, demonstrate the superiority of MDMTL over the state-of-the-art approaches." @default.
• W2894544906 created "2018-10-05" @default.
• W2894544906 creator A5001185571 @default.
• W2894544906 creator A5033713097 @default.
• W2894544906 creator A5046305086 @default.
• W2894544906 creator A5054900679 @default.
• W2894544906 creator A5081485810 @default.
• W2894544906 date "2019-02-01" @default.
• W2894544906 modified "2023-10-15" @default.
• W2894544906 title "Multi-Domain and Multi-Task Learning for Human Action Recognition" @default.
• W2894544906 cites W1566538838 @default.
• W2894544906 cites W1777221758 @default.
• W2894544906 cites W1785794460 @default.
• W2894544906 cites W1895641373 @default.
• W2894544906 cites W1895914852 @default.
• W2894544906 cites W1923026787 @default.
• W2894544906 cites W1970732218 @default.
• W2894544906 cites W1981160672 @default.
• W2894544906 cites W1983592444 @default.
• W2894544906 cites W1983705368 @default.
• W2894544906 cites W1984267840 @default.
• W2894544906 cites W1999192586 @default.
• W2894544906 cites W2002370809 @default.
• W2894544906 cites W2007786430 @default.
• W2894544906 cites W2008771257 @default.
• W2894544906 cites W2010243644 @default.
• W2894544906 cites W2010676632 @default.
• W2894544906 cites W2016726354 @default.
• W2894544906 cites W2018096278 @default.
• W2894544906 cites W2018537231 @default.
• W2894544906 cites W2021733262 @default.
• W2894544906 cites W2023719791 @default.
• W2894544906 cites W2025632878 @default.
• W2894544906 cites W2031823405 @default.
• W2894544906 cites W2032612424 @default.
• W2894544906 cites W2036043322 @default.
• W2894544906 cites W2051530877 @default.
• W2894544906 cites W2056339039 @default.
• W2894544906 cites W2063589813 @default.
• W2894544906 cites W2068611653 @default.
• W2894544906 cites W2075280134 @default.
• W2894544906 cites W2085735683 @default.
• W2894544906 cites W2099501835 @default.
• W2894544906 cites W2105101328 @default.
• W2894544906 cites W2107962625 @default.
• W2894544906 cites W2108154570 @default.
• W2894544906 cites W2112020727 @default.
• W2894544906 cites W2119799051 @default.
• W2894544906 cites W2126574503 @default.
• W2894544906 cites W2127201883 @default.
• W2894544906 cites W2127271355 @default.
• W2894544906 cites W2142194269 @default.
• W2894544906 cites W2143267104 @default.
• W2894544906 cites W2155268664 @default.
• W2894544906 cites W2157833637 @default.
• W2894544906 cites W2160547390 @default.
• W2894544906 cites W2161108669 @default.
• W2894544906 cites W2166070055 @default.
• W2894544906 cites W2166267120 @default.
• W2894544906 cites W2322020277 @default.
• W2894544906 cites W2326735091 @default.
• W2894544906 cites W2337845395 @default.
• W2894544906 cites W2344034899 @default.
• W2894544906 cites W2404218691 @default.
• W2894544906 cites W2441438155 @default.
• W2894544906 cites W2465570449 @default.
• W2894544906 cites W2475098969 @default.
• W2894544906 cites W2504559372 @default.
• W2894544906 cites W2510249351 @default.
• W2894544906 cites W2517537544 @default.
• W2894544906 cites W2520613337 @default.
• W2894544906 cites W2591961134 @default.
• W2894544906 cites W2745648337 @default.
• W2894544906 cites W2746007478 @default.
• W2894544906 cites W2748219818 @default.
• W2894544906 cites W2751733204 @default.
• W2894544906 cites W2753898203 @default.
• W2894544906 cites W2770240892 @default.
• W2894544906 cites W2963322354 @default.
• W2894544906 cites W2963524571 @default.
• W2894544906 cites W3987941 @default.
• W2894544906 doi "https://doi.org/10.1109/tip.2018.2872879" @default.
• W2894544906 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30281454" @default.
• W2894544906 hasPublicationYear "2019" @default.
• W2894544906 type Work @default.
• W2894544906 sameAs 2894544906 @default.
• W2894544906 citedByCount "42" @default.
• W2894544906 countsByYear W28945449062019 @default.
• W2894544906 countsByYear W28945449062020 @default.
• W2894544906 countsByYear W28945449062021 @default.
• W2894544906 countsByYear W28945449062022 @default.
• W2894544906 countsByYear W28945449062023 @default.
• W2894544906 crossrefType "journal-article" @default.
• W2894544906 hasAuthorship W2894544906A5001185571 @default.
• W2894544906 hasAuthorship W2894544906A5033713097 @default.
• W2894544906 hasAuthorship W2894544906A5046305086 @default.
• W2894544906 hasAuthorship W2894544906A5054900679 @default.
• W2894544906 hasAuthorship W2894544906A5081485810 @default.

• next