Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898073175> ?p ?o ?g. }
- W2898073175 endingPage "15" @default.
- W2898073175 startingPage "1" @default.
- W2898073175 abstract "We demonstrate a novel deep neural network capable of reconstructing human full body pose in real-time from 6 Inertial Measurement Units (IMUs) worn on the user's body. In doing so, we address several difficult challenges. First, the problem is severely under-constrained as multiple pose parameters produce the same IMU orientations. Second, capturing IMU data in conjunction with ground-truth poses is expensive and difficult to do in many target application scenarios (e.g., outdoors). Third, modeling temporal dependencies through non-linear optimization has proven effective in prior work but makes real-time prediction infeasible. To address this important limitation, we learn the temporal pose priors using deep learning. To learn from sufficient data, we synthesize IMU data from motion capture datasets. A bi-directional RNN architecture leverages past and future information that is available at training time. At test time, we deploy the network in a sliding window fashion, retaining real time capabilities. To evaluate our method, we recorded DIP-IMU, a dataset consisting of 10 subjects wearing 17 IMUs for validation in 64 sequences with 330 000 time instants; this constitutes the largest IMU dataset publicly available. We quantitatively evaluate our approach on multiple datasets and show results from a real-time implementation. DIP-IMU and the code are available for research purposes. 1" @default.
- W2898073175 created "2018-10-26" @default.
- W2898073175 creator A5025000908 @default.
- W2898073175 creator A5042626023 @default.
- W2898073175 creator A5044027671 @default.
- W2898073175 creator A5065396778 @default.
- W2898073175 creator A5068160818 @default.
- W2898073175 creator A5076908763 @default.
- W2898073175 date "2018-12-04" @default.
- W2898073175 modified "2023-10-11" @default.
- W2898073175 title "Deep inertial poser" @default.
- W2898073175 cites W1542947501 @default.
- W2898073175 cites W1938204631 @default.
- W2898073175 cites W1943191679 @default.
- W2898073175 cites W1967437522 @default.
- W2898073175 cites W1967554269 @default.
- W2898073175 cites W1982905909 @default.
- W2898073175 cites W2017249118 @default.
- W2898073175 cites W2027389517 @default.
- W2898073175 cites W2044618760 @default.
- W2898073175 cites W2049462432 @default.
- W2898073175 cites W2060280062 @default.
- W2898073175 cites W2064675550 @default.
- W2898073175 cites W2075402943 @default.
- W2898073175 cites W2092146246 @default.
- W2898073175 cites W2099333815 @default.
- W2898073175 cites W2101032778 @default.
- W2898073175 cites W2112324691 @default.
- W2898073175 cites W2113148808 @default.
- W2898073175 cites W2113325037 @default.
- W2898073175 cites W2122633688 @default.
- W2898073175 cites W2131389448 @default.
- W2898073175 cites W2131774270 @default.
- W2898073175 cites W2150457612 @default.
- W2898073175 cites W2152047877 @default.
- W2898073175 cites W2201021190 @default.
- W2898073175 cites W2307770531 @default.
- W2898073175 cites W2342006632 @default.
- W2898073175 cites W2461005315 @default.
- W2898073175 cites W2515603221 @default.
- W2898073175 cites W2525184802 @default.
- W2898073175 cites W2554986796 @default.
- W2898073175 cites W2605243700 @default.
- W2898073175 cites W2611706523 @default.
- W2898073175 cites W2611932403 @default.
- W2898073175 cites W2737762407 @default.
- W2898073175 cites W2739330054 @default.
- W2898073175 cites W2754534665 @default.
- W2898073175 cites W2767607256 @default.
- W2898073175 cites W2784646928 @default.
- W2898073175 cites W2793768642 @default.
- W2898073175 cites W2888934629 @default.
- W2898073175 cites W2895748257 @default.
- W2898073175 cites W2963150697 @default.
- W2898073175 cites W2963688992 @default.
- W2898073175 cites W2964203186 @default.
- W2898073175 cites W3139397654 @default.
- W2898073175 cites W4242146635 @default.
- W2898073175 cites W64404897 @default.
- W2898073175 doi "https://doi.org/10.1145/3272127.3275108" @default.
- W2898073175 hasPublicationYear "2018" @default.
- W2898073175 type Work @default.
- W2898073175 sameAs 2898073175 @default.
- W2898073175 citedByCount "148" @default.
- W2898073175 countsByYear W28980731752019 @default.
- W2898073175 countsByYear W28980731752020 @default.
- W2898073175 countsByYear W28980731752021 @default.
- W2898073175 countsByYear W28980731752022 @default.
- W2898073175 countsByYear W28980731752023 @default.
- W2898073175 crossrefType "journal-article" @default.
- W2898073175 hasAuthorship W2898073175A5025000908 @default.
- W2898073175 hasAuthorship W2898073175A5042626023 @default.
- W2898073175 hasAuthorship W2898073175A5044027671 @default.
- W2898073175 hasAuthorship W2898073175A5065396778 @default.
- W2898073175 hasAuthorship W2898073175A5068160818 @default.
- W2898073175 hasAuthorship W2898073175A5076908763 @default.
- W2898073175 hasBestOaLocation W28980731751 @default.
- W2898073175 hasConcept C102392041 @default.
- W2898073175 hasConcept C104114177 @default.
- W2898073175 hasConcept C108583219 @default.
- W2898073175 hasConcept C111919701 @default.
- W2898073175 hasConcept C121332964 @default.
- W2898073175 hasConcept C146849305 @default.
- W2898073175 hasConcept C151233233 @default.
- W2898073175 hasConcept C154945302 @default.
- W2898073175 hasConcept C173386949 @default.
- W2898073175 hasConcept C2778751112 @default.
- W2898073175 hasConcept C31972630 @default.
- W2898073175 hasConcept C41008148 @default.
- W2898073175 hasConcept C48007421 @default.
- W2898073175 hasConcept C62520636 @default.
- W2898073175 hasConcept C79061980 @default.
- W2898073175 hasConceptScore W2898073175C102392041 @default.
- W2898073175 hasConceptScore W2898073175C104114177 @default.
- W2898073175 hasConceptScore W2898073175C108583219 @default.
- W2898073175 hasConceptScore W2898073175C111919701 @default.
- W2898073175 hasConceptScore W2898073175C121332964 @default.
- W2898073175 hasConceptScore W2898073175C146849305 @default.