Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964203186> ?p ?o ?g. }
- W2964203186 abstract "Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following the success of deep learning methods in several computer vision tasks, recent work has focused on using deep recurrent neural networks (RNNs) to model human motion, with the goal of learning time-dependent representations that perform tasks such as short-term motion prediction and long-term human motion synthesis. We examine recent work, with a focus on the evaluation methodologies commonly used in the literature, and show that, surprisingly, state of the art performance can be achieved by a simple baseline that does not attempt to model motion at all. We investigate this result, and analyze recent RNN methods by looking at the architectures, loss functions, and training procedures used in state-of-the-art approaches. We propose three changes to the standard RNN models typically used for human motion, which results in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction." @default.
- W2964203186 created "2019-07-30" @default.
- W2964203186 creator A5055061909 @default.
- W2964203186 creator A5065396778 @default.
- W2964203186 creator A5070528616 @default.
- W2964203186 date "2017-07-01" @default.
- W2964203186 modified "2023-10-11" @default.
- W2964203186 title "On Human Motion Prediction Using Recurrent Neural Networks" @default.
- W2964203186 cites W1488195763 @default.
- W2964203186 cites W1735317348 @default.
- W2964203186 cites W1865572126 @default.
- W2964203186 cites W1990429558 @default.
- W2964203186 cites W2030991373 @default.
- W2964203186 cites W2048821851 @default.
- W2964203186 cites W2057232399 @default.
- W2964203186 cites W2097278008 @default.
- W2964203186 cites W2097412577 @default.
- W2964203186 cites W2101032778 @default.
- W2964203186 cites W2102630415 @default.
- W2964203186 cites W2118646811 @default.
- W2964203186 cites W2141049796 @default.
- W2964203186 cites W2142192571 @default.
- W2964203186 cites W2144481990 @default.
- W2964203186 cites W2148578241 @default.
- W2964203186 cites W2154053313 @default.
- W2964203186 cites W2171184283 @default.
- W2964203186 cites W2176429381 @default.
- W2964203186 cites W2194775991 @default.
- W2964203186 cites W2293741035 @default.
- W2964203186 cites W2296073425 @default.
- W2964203186 cites W2442651457 @default.
- W2964203186 cites W2462496837 @default.
- W2964203186 cites W2964199361 @default.
- W2964203186 cites W4205471895 @default.
- W2964203186 cites W4231947169 @default.
- W2964203186 cites W4248876013 @default.
- W2964203186 cites W4250902883 @default.
- W2964203186 doi "https://doi.org/10.1109/cvpr.2017.497" @default.
- W2964203186 hasPublicationYear "2017" @default.
- W2964203186 type Work @default.
- W2964203186 sameAs 2964203186 @default.
- W2964203186 citedByCount "545" @default.
- W2964203186 countsByYear W29642031862017 @default.
- W2964203186 countsByYear W29642031862018 @default.
- W2964203186 countsByYear W29642031862019 @default.
- W2964203186 countsByYear W29642031862020 @default.
- W2964203186 countsByYear W29642031862021 @default.
- W2964203186 countsByYear W29642031862022 @default.
- W2964203186 countsByYear W29642031862023 @default.
- W2964203186 crossrefType "proceedings-article" @default.
- W2964203186 hasAuthorship W2964203186A5055061909 @default.
- W2964203186 hasAuthorship W2964203186A5065396778 @default.
- W2964203186 hasAuthorship W2964203186A5070528616 @default.
- W2964203186 hasBestOaLocation W29642031862 @default.
- W2964203186 hasConcept C10161872 @default.
- W2964203186 hasConcept C104114177 @default.
- W2964203186 hasConcept C108583219 @default.
- W2964203186 hasConcept C119857082 @default.
- W2964203186 hasConcept C120665830 @default.
- W2964203186 hasConcept C121332964 @default.
- W2964203186 hasConcept C127413603 @default.
- W2964203186 hasConcept C146978453 @default.
- W2964203186 hasConcept C147168706 @default.
- W2964203186 hasConcept C154945302 @default.
- W2964203186 hasConcept C192209626 @default.
- W2964203186 hasConcept C31972630 @default.
- W2964203186 hasConcept C41008148 @default.
- W2964203186 hasConcept C48007421 @default.
- W2964203186 hasConcept C48044578 @default.
- W2964203186 hasConcept C50644808 @default.
- W2964203186 hasConcept C64543145 @default.
- W2964203186 hasConcept C77088390 @default.
- W2964203186 hasConcept C77660652 @default.
- W2964203186 hasConceptScore W2964203186C10161872 @default.
- W2964203186 hasConceptScore W2964203186C104114177 @default.
- W2964203186 hasConceptScore W2964203186C108583219 @default.
- W2964203186 hasConceptScore W2964203186C119857082 @default.
- W2964203186 hasConceptScore W2964203186C120665830 @default.
- W2964203186 hasConceptScore W2964203186C121332964 @default.
- W2964203186 hasConceptScore W2964203186C127413603 @default.
- W2964203186 hasConceptScore W2964203186C146978453 @default.
- W2964203186 hasConceptScore W2964203186C147168706 @default.
- W2964203186 hasConceptScore W2964203186C154945302 @default.
- W2964203186 hasConceptScore W2964203186C192209626 @default.
- W2964203186 hasConceptScore W2964203186C31972630 @default.
- W2964203186 hasConceptScore W2964203186C41008148 @default.
- W2964203186 hasConceptScore W2964203186C48007421 @default.
- W2964203186 hasConceptScore W2964203186C48044578 @default.
- W2964203186 hasConceptScore W2964203186C50644808 @default.
- W2964203186 hasConceptScore W2964203186C64543145 @default.
- W2964203186 hasConceptScore W2964203186C77088390 @default.
- W2964203186 hasConceptScore W2964203186C77660652 @default.
- W2964203186 hasLocation W29642031861 @default.
- W2964203186 hasLocation W29642031862 @default.
- W2964203186 hasOpenAccess W2964203186 @default.
- W2964203186 hasPrimaryLocation W29642031861 @default.
- W2964203186 hasRelatedWork W1546047669 @default.
- W2964203186 hasRelatedWork W1898762316 @default.
- W2964203186 hasRelatedWork W2029249305 @default.
- W2964203186 hasRelatedWork W2119189625 @default.