FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100772652> ?p ?o ?g. }

• W3100772652 endingPage "59" @default.
• W3100772652 startingPage "39" @default.
• W3100772652 abstract "In the scope of gestural action recognition, the size of the feature vector representing movements is in general quite large especially when full body movements are considered. Furthermore, this feature vector evolves during the movement performance so that a complete movement is fully represented by a matrix M of size DxT , whose element M i, j represents the value of feature i at timestamps j. Many studies have addressed dimensionality reduction considering only the size of the feature vector lying in R D to reduce both the variability of gestural sequences expressed in the reduced space, and the computational complexity of their processing. In return, very few of these methods have explicitly addressed the dimensionality reduction along the time axis. Yet this is a major issue when considering the use of elastic distances which are characterized by a quadratic complexity along the time axis. We present in this paper an evaluation of straightforward approaches aiming at reducing the dimensionality of the matrix M for each movement, leading to consider both the dimensionality reduction of the feature vector as well as its reduction along the time axis. The dimensionality reduction of the feature vector is achieved by selecting remarkable joints in the skeleton performing the movement, basically the extremities of the articulatory chains composing the skeleton. The temporal dimen-sionality reduction is achieved using either a regular or adaptive down-sampling that seeks to minimize the reconstruction error of the movements. Elastic and Euclidean kernels are then compared through support vector machine learning. Two data sets 1 that are widely referenced in the domain of human gesture recognition, and quite distinctive in terms of quality of motion capture, are used for the experimental assessment of the proposed approaches. On these data sets we experimentally show that it is feasible, and possibly desirable, to significantly reduce simultaneously the size of the feature vector and the number of skeleton frames to represent body movements while maintaining a very good recognition rate. The method proves to give satisfactory results at a level currently reached by state-of-the-art methods on these data sets. We experimentally show that the computational complexity reduction that is obtained makes this approach eligible for real-time applications." @default.
• W3100772652 created "2020-11-23" @default.
• W3100772652 creator A5004992141 @default.
• W3100772652 creator A5006514699 @default.
• W3100772652 creator A5037347942 @default.
• W3100772652 date "2016-11-04" @default.
• W3100772652 modified "2023-10-18" @default.
• W3100772652 title "Adaptive Down-Sampling and Dimension Reduction in Time Elastic Kernel Machines for Efficient Recognition of Isolated Gestures" @default.
• W3100772652 cites W1490943637 @default.
• W3100772652 cites W1520610562 @default.
• W3100772652 cites W1594815103 @default.
• W3100772652 cites W179694669 @default.
• W3100772652 cites W1936711609 @default.
• W3100772652 cites W1966554111 @default.
• W3100772652 cites W1986092967 @default.
• W3100772652 cites W1995113806 @default.
• W3100772652 cites W2001141328 @default.
• W3100772652 cites W2023555797 @default.
• W3100772652 cites W2030991373 @default.
• W3100772652 cites W2053186076 @default.
• W3100772652 cites W2063512338 @default.
• W3100772652 cites W2068915126 @default.
• W3100772652 cites W2085735683 @default.
• W3100772652 cites W2097308346 @default.
• W3100772652 cites W2124635854 @default.
• W3100772652 cites W2124958607 @default.
• W3100772652 cites W2125073690 @default.
• W3100772652 cites W2129620337 @default.
• W3100772652 cites W2133600694 @default.
• W3100772652 cites W2143267104 @default.
• W3100772652 cites W2143325592 @default.
• W3100772652 cites W2144380653 @default.
• W3100772652 cites W2147389064 @default.
• W3100772652 cites W2153635508 @default.
• W3100772652 cites W2158301611 @default.
• W3100772652 cites W2168392347 @default.
• W3100772652 cites W2172156083 @default.
• W3100772652 cites W3104580753 @default.
• W3100772652 cites W4246354968 @default.
• W3100772652 cites W4292023222 @default.
• W3100772652 doi "https://doi.org/10.1007/978-3-319-45763-5_3" @default.
• W3100772652 hasPublicationYear "2016" @default.
• W3100772652 type Work @default.
• W3100772652 sameAs 3100772652 @default.
• W3100772652 citedByCount "0" @default.
• W3100772652 crossrefType "book-chapter" @default.
• W3100772652 hasAuthorship W3100772652A5004992141 @default.
• W3100772652 hasAuthorship W3100772652A5006514699 @default.
• W3100772652 hasAuthorship W3100772652A5037347942 @default.
• W3100772652 hasBestOaLocation W31007726522 @default.
• W3100772652 hasConcept C106487976 @default.
• W3100772652 hasConcept C111030470 @default.
• W3100772652 hasConcept C111335779 @default.
• W3100772652 hasConcept C11413529 @default.
• W3100772652 hasConcept C114614502 @default.
• W3100772652 hasConcept C138885662 @default.
• W3100772652 hasConcept C153180895 @default.
• W3100772652 hasConcept C154945302 @default.
• W3100772652 hasConcept C159985019 @default.
• W3100772652 hasConcept C192562407 @default.
• W3100772652 hasConcept C2524010 @default.
• W3100772652 hasConcept C2776401178 @default.
• W3100772652 hasConcept C33676613 @default.
• W3100772652 hasConcept C33923547 @default.
• W3100772652 hasConcept C41008148 @default.
• W3100772652 hasConcept C41895202 @default.
• W3100772652 hasConcept C70518039 @default.
• W3100772652 hasConcept C83665646 @default.
• W3100772652 hasConceptScore W3100772652C106487976 @default.
• W3100772652 hasConceptScore W3100772652C111030470 @default.
• W3100772652 hasConceptScore W3100772652C111335779 @default.
• W3100772652 hasConceptScore W3100772652C11413529 @default.
• W3100772652 hasConceptScore W3100772652C114614502 @default.
• W3100772652 hasConceptScore W3100772652C138885662 @default.
• W3100772652 hasConceptScore W3100772652C153180895 @default.
• W3100772652 hasConceptScore W3100772652C154945302 @default.
• W3100772652 hasConceptScore W3100772652C159985019 @default.
• W3100772652 hasConceptScore W3100772652C192562407 @default.
• W3100772652 hasConceptScore W3100772652C2524010 @default.
• W3100772652 hasConceptScore W3100772652C2776401178 @default.
• W3100772652 hasConceptScore W3100772652C33676613 @default.
• W3100772652 hasConceptScore W3100772652C33923547 @default.
• W3100772652 hasConceptScore W3100772652C41008148 @default.
• W3100772652 hasConceptScore W3100772652C41895202 @default.
• W3100772652 hasConceptScore W3100772652C70518039 @default.
• W3100772652 hasConceptScore W3100772652C83665646 @default.
• W3100772652 hasLocation W31007726521 @default.
• W3100772652 hasLocation W31007726522 @default.
• W3100772652 hasLocation W31007726523 @default.
• W3100772652 hasLocation W31007726524 @default.
• W3100772652 hasLocation W31007726525 @default.
• W3100772652 hasOpenAccess W3100772652 @default.
• W3100772652 hasPrimaryLocation W31007726521 @default.
• W3100772652 hasRelatedWork W2048060766 @default.
• W3100772652 hasRelatedWork W2053724255 @default.
• W3100772652 hasRelatedWork W2066259560 @default.
• W3100772652 hasRelatedWork W2071887232 @default.
• W3100772652 hasRelatedWork W2097193191 @default.

• next