FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894957992> ?p ?o ?g. }

• W2894957992 endingPage "43" @default.
• W2894957992 startingPage "32" @default.
• W2894957992 abstract "In this article, we introduce a fast, accurate and invariant method for RGB-D based human action recognition using a Hierarchical Kinematic Covariance (HKC) descriptor. Recently, non singular covariance matrices of pattern features which are elements of the space of Symmetric Definite Positive (SPD) matrices, have been proven to be very efficient descriptors in the field of pattern recognition. However, in the case of action recognition, singular covariance matrices cannot be avoided because the dimension of features could be higher than the number of samples. Such covariance matrices (non singular and singular) belong to the space of Symmetric Positive semi-Definite (SPsD) matrices. Thus, in order to classify actions, we propose to adapt kernel methods such as Support Vector Machines (SVM) and Multiple Kernel Learning (MKL) to the space of SPsD matrices by using a perturbed Log-Euclidean distance (Arsigny et al., 2006). The mathematical validity of this perturbed distance (called Modified Log-Euclidean distance) for SPsD is therefore studied. The offline experiments are conducted on three challenging benchmarks, namely MSRAction3D, UTKinect and Multiview3D datasets. A fair comparison demonstrates that our approach competes with state-of-the-art methods in terms of accuracy and computational latency. Finally, our method is extended to an online scenario and experiments on MSRC12 prove the efficiency of this extension." @default.
• W2894957992 created "2018-10-12" @default.
• W2894957992 creator A5005772420 @default.
• W2894957992 creator A5013194782 @default.
• W2894957992 creator A5030348427 @default.
• W2894957992 creator A5069505366 @default.
• W2894957992 creator A5080787031 @default.
• W2894957992 date "2018-10-01" @default.
• W2894957992 modified "2023-09-30" @default.
• W2894957992 title "An extension of kernel learning methods using a modified Log-Euclidean distance for fast and accurate skeleton-based Human Action Recognition" @default.
• W2894957992 cites W1549083695 @default.
• W2894957992 cites W1592510033 @default.
• W2894957992 cites W1777221758 @default.
• W2894957992 cites W1983592444 @default.
• W2894957992 cites W1986964250 @default.
• W2894957992 cites W1995113806 @default.
• W2894957992 cites W1998167411 @default.
• W2894957992 cites W2005577322 @default.
• W2894957992 cites W2007057255 @default.
• W2894957992 cites W2021150171 @default.
• W2894957992 cites W2048192550 @default.
• W2894957992 cites W2048821851 @default.
• W2894957992 cites W2060280062 @default.
• W2894957992 cites W2085735683 @default.
• W2894957992 cites W2091911422 @default.
• W2894957992 cites W2098339052 @default.
• W2894957992 cites W2099634219 @default.
• W2894957992 cites W2106996050 @default.
• W2894957992 cites W2116087095 @default.
• W2894957992 cites W2120852116 @default.
• W2894957992 cites W2125583080 @default.
• W2894957992 cites W2133848164 @default.
• W2894957992 cites W2143267104 @default.
• W2894957992 cites W2144380653 @default.
• W2894957992 cites W2145546283 @default.
• W2894957992 cites W2149652297 @default.
• W2894957992 cites W2160253527 @default.
• W2894957992 cites W2182587296 @default.
• W2894957992 cites W2341234201 @default.
• W2894957992 cites W2344034899 @default.
• W2894957992 cites W2344822974 @default.
• W2894957992 cites W2466991859 @default.
• W2894957992 cites W2609494734 @default.
• W2894957992 cites W2881486721 @default.
• W2894957992 cites W2963117523 @default.
• W2894957992 cites W2963162443 @default.
• W2894957992 doi "https://doi.org/10.1016/j.cviu.2018.09.004" @default.
• W2894957992 hasPublicationYear "2018" @default.
• W2894957992 type Work @default.
• W2894957992 sameAs 2894957992 @default.
• W2894957992 citedByCount "10" @default.
• W2894957992 countsByYear W28949579922019 @default.
• W2894957992 countsByYear W28949579922020 @default.
• W2894957992 countsByYear W28949579922021 @default.
• W2894957992 crossrefType "journal-article" @default.
• W2894957992 hasAuthorship W2894957992A5005772420 @default.
• W2894957992 hasAuthorship W2894957992A5013194782 @default.
• W2894957992 hasAuthorship W2894957992A5030348427 @default.
• W2894957992 hasAuthorship W2894957992A5069505366 @default.
• W2894957992 hasAuthorship W2894957992A5080787031 @default.
• W2894957992 hasBestOaLocation W28949579922 @default.
• W2894957992 hasConcept C105795698 @default.
• W2894957992 hasConcept C11413529 @default.
• W2894957992 hasConcept C118615104 @default.
• W2894957992 hasConcept C120174047 @default.
• W2894957992 hasConcept C153180895 @default.
• W2894957992 hasConcept C154945302 @default.
• W2894957992 hasConcept C178650346 @default.
• W2894957992 hasConcept C33923547 @default.
• W2894957992 hasConcept C41008148 @default.
• W2894957992 hasConcept C74193536 @default.
• W2894957992 hasConceptScore W2894957992C105795698 @default.
• W2894957992 hasConceptScore W2894957992C11413529 @default.
• W2894957992 hasConceptScore W2894957992C118615104 @default.
• W2894957992 hasConceptScore W2894957992C120174047 @default.
• W2894957992 hasConceptScore W2894957992C153180895 @default.
• W2894957992 hasConceptScore W2894957992C154945302 @default.
• W2894957992 hasConceptScore W2894957992C178650346 @default.
• W2894957992 hasConceptScore W2894957992C33923547 @default.
• W2894957992 hasConceptScore W2894957992C41008148 @default.
• W2894957992 hasConceptScore W2894957992C74193536 @default.
• W2894957992 hasLocation W28949579921 @default.
• W2894957992 hasLocation W28949579922 @default.
• W2894957992 hasLocation W28949579923 @default.
• W2894957992 hasLocation W28949579924 @default.
• W2894957992 hasOpenAccess W2894957992 @default.
• W2894957992 hasPrimaryLocation W28949579921 @default.
• W2894957992 hasRelatedWork W1981015757 @default.
• W2894957992 hasRelatedWork W2011404346 @default.
• W2894957992 hasRelatedWork W2024105718 @default.
• W2894957992 hasRelatedWork W2033914206 @default.
• W2894957992 hasRelatedWork W2048963143 @default.
• W2894957992 hasRelatedWork W2110459882 @default.
• W2894957992 hasRelatedWork W2146076056 @default.
• W2894957992 hasRelatedWork W2335037768 @default.
• W2894957992 hasRelatedWork W2410198229 @default.
• W2894957992 hasRelatedWork W2974128303 @default.
• W2894957992 hasVolume "175" @default.

• next