Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945132220> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2945132220 endingPage "66335" @default.
- W2945132220 startingPage "66325" @default.
- W2945132220 abstract "Human motion synthesis technology has a very important position in computer animation, and it is widely used in medicine, film and television, motion analysis, games, and other related fields. The synthesis of human motion is the virtual of the action of the characters in the real world, the authenticity of the action, and the natural smoothness is especially important to the user's experience. Due to the complexity of human structure, how to generate a high-quality movement is a challenging task. The data used in this paper are all 3D human motion data in BioVision Hierarchical (BVH) format, which can be captured by optical, inertial, mechanical or other video-based motion capture devices. In this paper, first, a three-layer convolutional neural network was used to output mapping in the hidden unit of the input motion capture data. Then, a one-dimensional convolution auto-encoder was connected; meanwhile, the bone length constraint, position constraint, and trajectory constraint were added. It repaired the non-inertial joints of motion data and removed the motion artifacts. To achieve the synthesis of the two motions, we extracted the style transformation in the motion, added style and content constraints, and finally output the motion. To verify the feasibility of the algorithm, we obtained the animation effect of the synthesized motion by testing the input motion. The experimental results show that the motions synthesized by the proposed algorithm not only look natural smooth in visual effect but also reduce the time consumed by about 42.6% compared with the existing algorithms." @default.
- W2945132220 created "2019-05-29" @default.
- W2945132220 creator A5003257736 @default.
- W2945132220 creator A5005780325 @default.
- W2945132220 creator A5036365985 @default.
- W2945132220 creator A5042603313 @default.
- W2945132220 creator A5053795352 @default.
- W2945132220 creator A5055447805 @default.
- W2945132220 creator A5068792201 @default.
- W2945132220 date "2019-01-01" @default.
- W2945132220 modified "2023-10-16" @default.
- W2945132220 title "3D Human Motion Synthesis Based on Convolutional Neural Network" @default.
- W2945132220 cites W1735317348 @default.
- W2945132220 cites W1977273805 @default.
- W2945132220 cites W2010556676 @default.
- W2945132220 cites W2032893275 @default.
- W2945132220 cites W2049077434 @default.
- W2945132220 cites W2066421970 @default.
- W2945132220 cites W2105433999 @default.
- W2945132220 cites W2124609748 @default.
- W2945132220 cites W2460926736 @default.
- W2945132220 cites W2469134594 @default.
- W2945132220 cites W2471723840 @default.
- W2945132220 cites W2573854917 @default.
- W2945132220 cites W2607626373 @default.
- W2945132220 cites W2608653446 @default.
- W2945132220 cites W2738109755 @default.
- W2945132220 cites W2780432148 @default.
- W2945132220 cites W2797184202 @default.
- W2945132220 cites W2802441648 @default.
- W2945132220 cites W2963688992 @default.
- W2945132220 cites W2964203186 @default.
- W2945132220 doi "https://doi.org/10.1109/access.2019.2917609" @default.
- W2945132220 hasPublicationYear "2019" @default.
- W2945132220 type Work @default.
- W2945132220 sameAs 2945132220 @default.
- W2945132220 citedByCount "3" @default.
- W2945132220 countsByYear W29451322202021 @default.
- W2945132220 countsByYear W29451322202022 @default.
- W2945132220 crossrefType "journal-article" @default.
- W2945132220 hasAuthorship W2945132220A5003257736 @default.
- W2945132220 hasAuthorship W2945132220A5005780325 @default.
- W2945132220 hasAuthorship W2945132220A5036365985 @default.
- W2945132220 hasAuthorship W2945132220A5042603313 @default.
- W2945132220 hasAuthorship W2945132220A5053795352 @default.
- W2945132220 hasAuthorship W2945132220A5055447805 @default.
- W2945132220 hasAuthorship W2945132220A5068792201 @default.
- W2945132220 hasBestOaLocation W29451322201 @default.
- W2945132220 hasConcept C104114177 @default.
- W2945132220 hasConcept C154945302 @default.
- W2945132220 hasConcept C31972630 @default.
- W2945132220 hasConcept C41008148 @default.
- W2945132220 hasConcept C81363708 @default.
- W2945132220 hasConceptScore W2945132220C104114177 @default.
- W2945132220 hasConceptScore W2945132220C154945302 @default.
- W2945132220 hasConceptScore W2945132220C31972630 @default.
- W2945132220 hasConceptScore W2945132220C41008148 @default.
- W2945132220 hasConceptScore W2945132220C81363708 @default.
- W2945132220 hasFunder F4320321001 @default.
- W2945132220 hasFunder F4320336125 @default.
- W2945132220 hasLocation W29451322201 @default.
- W2945132220 hasOpenAccess W2945132220 @default.
- W2945132220 hasPrimaryLocation W29451322201 @default.
- W2945132220 hasRelatedWork W1926323357 @default.
- W2945132220 hasRelatedWork W2029249305 @default.
- W2945132220 hasRelatedWork W2115571026 @default.
- W2945132220 hasRelatedWork W2144043954 @default.
- W2945132220 hasRelatedWork W2511137960 @default.
- W2945132220 hasRelatedWork W2604231787 @default.
- W2945132220 hasRelatedWork W2610014769 @default.
- W2945132220 hasRelatedWork W2687972263 @default.
- W2945132220 hasRelatedWork W2895616727 @default.
- W2945132220 hasRelatedWork W3214088465 @default.
- W2945132220 hasVolume "7" @default.
- W2945132220 isParatext "false" @default.
- W2945132220 isRetracted "false" @default.
- W2945132220 magId "2945132220" @default.
- W2945132220 workType "article" @default.