Matches in SemOpenAlex for { <https://semopenalex.org/work/W3214492097> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3214492097 endingPage "108424" @default.
- W3214492097 startingPage "108424" @default.
- W3214492097 abstract "Forecasting human motion from a sequence of human poses is an important problem in the fields of computer vision and robotics. Most previous approaches merely consider learning the temporal dynamics of body joints or joint angles, while neglect derivatives of body joints (i.e., pose velocities) which could reasonably reduce noise impact and improve stability. To exploit the benefits of pose velocities, we propose the velocity-to-velocity learning paradigm for human motion prediction which attempts to directly build the sequence-to-sequence model in the velocity space. Two variant architectures based on recurrent encoder-decoder networks are introduced under this paradigm. Considering human motion as kinematics of rigid bodies, joint angles which denote transformation are the computations of inverse kinematics. Accordingly, a novel loss function in terms of rotation matrices is designed during training for human motion prediction through a rotation matrix transformation (RMT) layer. Finally, we present an effective training algorithm which exploits sequence transformation to improve model generalization. Our approaches substantially outperform state-of-the-art approaches on two large-scale datasets, Human3.6M and CMU Motion Capture, for both short-term prediction and long-term prediction. In particular, our model can competently forecast human-like and meaningful poses up to 1000 milliseconds. The code is available on GitHub: https://github.com/hongsong-wang/RNN_based_human_motion_prediction." @default.
- W3214492097 created "2021-11-22" @default.
- W3214492097 creator A5014269015 @default.
- W3214492097 creator A5033884558 @default.
- W3214492097 creator A5086664647 @default.
- W3214492097 creator A5089053875 @default.
- W3214492097 date "2022-04-01" @default.
- W3214492097 modified "2023-10-16" @default.
- W3214492097 title "Velocity-to-velocity human motion forecasting" @default.
- W3214492097 cites W1977259876 @default.
- W3214492097 cites W2064675550 @default.
- W3214492097 cites W2101032778 @default.
- W3214492097 cites W2184544926 @default.
- W3214492097 cites W2469134594 @default.
- W3214492097 cites W2593146028 @default.
- W3214492097 cites W2726019568 @default.
- W3214492097 cites W2794597556 @default.
- W3214492097 cites W2803158089 @default.
- W3214492097 cites W3036644940 @default.
- W3214492097 cites W3176882544 @default.
- W3214492097 doi "https://doi.org/10.1016/j.patcog.2021.108424" @default.
- W3214492097 hasPublicationYear "2022" @default.
- W3214492097 type Work @default.
- W3214492097 sameAs 3214492097 @default.
- W3214492097 citedByCount "2" @default.
- W3214492097 countsByYear W32144920972023 @default.
- W3214492097 crossrefType "journal-article" @default.
- W3214492097 hasAuthorship W3214492097A5014269015 @default.
- W3214492097 hasAuthorship W3214492097A5033884558 @default.
- W3214492097 hasAuthorship W3214492097A5086664647 @default.
- W3214492097 hasAuthorship W3214492097A5089053875 @default.
- W3214492097 hasConcept C104114177 @default.
- W3214492097 hasConcept C104317684 @default.
- W3214492097 hasConcept C11413529 @default.
- W3214492097 hasConcept C121332964 @default.
- W3214492097 hasConcept C134306372 @default.
- W3214492097 hasConcept C154945302 @default.
- W3214492097 hasConcept C177148314 @default.
- W3214492097 hasConcept C185592680 @default.
- W3214492097 hasConcept C204241405 @default.
- W3214492097 hasConcept C2778112365 @default.
- W3214492097 hasConcept C31972630 @default.
- W3214492097 hasConcept C33923547 @default.
- W3214492097 hasConcept C34413123 @default.
- W3214492097 hasConcept C39920418 @default.
- W3214492097 hasConcept C41008148 @default.
- W3214492097 hasConcept C54355233 @default.
- W3214492097 hasConcept C55493867 @default.
- W3214492097 hasConcept C74050887 @default.
- W3214492097 hasConcept C74650414 @default.
- W3214492097 hasConcept C86803240 @default.
- W3214492097 hasConcept C90509273 @default.
- W3214492097 hasConceptScore W3214492097C104114177 @default.
- W3214492097 hasConceptScore W3214492097C104317684 @default.
- W3214492097 hasConceptScore W3214492097C11413529 @default.
- W3214492097 hasConceptScore W3214492097C121332964 @default.
- W3214492097 hasConceptScore W3214492097C134306372 @default.
- W3214492097 hasConceptScore W3214492097C154945302 @default.
- W3214492097 hasConceptScore W3214492097C177148314 @default.
- W3214492097 hasConceptScore W3214492097C185592680 @default.
- W3214492097 hasConceptScore W3214492097C204241405 @default.
- W3214492097 hasConceptScore W3214492097C2778112365 @default.
- W3214492097 hasConceptScore W3214492097C31972630 @default.
- W3214492097 hasConceptScore W3214492097C33923547 @default.
- W3214492097 hasConceptScore W3214492097C34413123 @default.
- W3214492097 hasConceptScore W3214492097C39920418 @default.
- W3214492097 hasConceptScore W3214492097C41008148 @default.
- W3214492097 hasConceptScore W3214492097C54355233 @default.
- W3214492097 hasConceptScore W3214492097C55493867 @default.
- W3214492097 hasConceptScore W3214492097C74050887 @default.
- W3214492097 hasConceptScore W3214492097C74650414 @default.
- W3214492097 hasConceptScore W3214492097C86803240 @default.
- W3214492097 hasConceptScore W3214492097C90509273 @default.
- W3214492097 hasLocation W32144920971 @default.
- W3214492097 hasOpenAccess W3214492097 @default.
- W3214492097 hasPrimaryLocation W32144920971 @default.
- W3214492097 hasRelatedWork W2029249305 @default.
- W3214492097 hasRelatedWork W2033423548 @default.
- W3214492097 hasRelatedWork W2115571026 @default.
- W3214492097 hasRelatedWork W2393116105 @default.
- W3214492097 hasRelatedWork W2401401198 @default.
- W3214492097 hasRelatedWork W2503725501 @default.
- W3214492097 hasRelatedWork W2511137960 @default.
- W3214492097 hasRelatedWork W2604231787 @default.
- W3214492097 hasRelatedWork W2687972263 @default.
- W3214492097 hasRelatedWork W3214088465 @default.
- W3214492097 hasVolume "124" @default.
- W3214492097 isParatext "false" @default.
- W3214492097 isRetracted "false" @default.
- W3214492097 magId "3214492097" @default.
- W3214492097 workType "article" @default.