FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891718801> ?p ?o ?g. }

• W2891718801 endingPage "397" @default.
• W2891718801 startingPage "381" @default.
• W2891718801 abstract "We propose an approach to accurately estimate 3D human pose by fusing multi-viewpoint video (MVV) with inertial measurement unit (IMU) sensor data, without optical markers, a complex hardware setup or a full body model. Uniquely we use a multi-channel 3D convolutional neural network to learn a pose embedding from visual occupancy and semantic 2D pose estimates from the MVV in a discretised volumetric probabilistic visual hull. The learnt pose stream is concurrently processed with a forward kinematic solve of the IMU data and a temporal model (LSTM) exploits the rich spatial and temporal long range dependencies among the solved joints, the two streams are then fused in a final fully connected layer. The two complementary data sources allow for ambiguities to be resolved within each sensor modality, yielding improved accuracy over prior methods. Extensive evaluation is performed with state of the art performance reported on the popular Human 3.6M dataset (Ionescu et al. in Intell IEEE Trans Pattern Anal Mach 36(7):1325–1339, 2014), the newly released TotalCapture dataset and a challenging set of outdoor videos TotalCaptureOutdoor. We release the new hybrid MVV dataset (TotalCapture) comprising of multi-viewpoint video, IMU and accurate 3D skeletal joint ground truth derived from a commercial motion capture system. The dataset is available online at http://cvssp.org/data/totalcapture/ ." @default.
• W2891718801 created "2018-09-27" @default.
• W2891718801 creator A5016376222 @default.
• W2891718801 creator A5019810821 @default.
• W2891718801 creator A5024767797 @default.
• W2891718801 creator A5028114716 @default.
• W2891718801 creator A5090342811 @default.
• W2891718801 date "2018-09-08" @default.
• W2891718801 modified "2023-09-25" @default.
• W2891718801 title "Fusing Visual and Inertial Sensors with Semantics for 3D Human Pose Estimation" @default.
• W2891718801 cites W1542947501 @default.
• W2891718801 cites W1861492603 @default.
• W2891718801 cites W1947481528 @default.
• W2891718801 cites W1950149599 @default.
• W2891718801 cites W1967554269 @default.
• W2891718801 cites W2017249118 @default.
• W2891718801 cites W2018793343 @default.
• W2891718801 cites W2027389517 @default.
• W2891718801 cites W2052678124 @default.
• W2891718801 cites W2064675550 @default.
• W2891718801 cites W2080873731 @default.
• W2891718801 cites W2083975035 @default.
• W2891718801 cites W2089665312 @default.
• W2891718801 cites W2099333815 @default.
• W2891718801 cites W2101032778 @default.
• W2891718801 cites W2108598243 @default.
• W2891718801 cites W2112324691 @default.
• W2891718801 cites W2125457700 @default.
• W2891718801 cites W2152047877 @default.
• W2891718801 cites W2158268505 @default.
• W2891718801 cites W2293634267 @default.
• W2891718801 cites W2333544554 @default.
• W2891718801 cites W2424778531 @default.
• W2891718801 cites W2495081533 @default.
• W2891718801 cites W2520324844 @default.
• W2891718801 cites W2554247908 @default.
• W2891718801 cites W2554986796 @default.
• W2891718801 cites W2555849634 @default.
• W2891718801 cites W2559085405 @default.
• W2891718801 cites W2573098616 @default.
• W2891718801 cites W2583372902 @default.
• W2891718801 cites W2605243700 @default.
• W2891718801 cites W2754534665 @default.
• W2891718801 cites W2784646928 @default.
• W2891718801 cites W2810607340 @default.
• W2891718801 cites W2963688992 @default.
• W2891718801 cites W2963772981 @default.
• W2891718801 cites W2964304707 @default.
• W2891718801 cites W4251108253 @default.
• W2891718801 doi "https://doi.org/10.1007/s11263-018-1118-y" @default.
• W2891718801 hasPublicationYear "2018" @default.
• W2891718801 type Work @default.
• W2891718801 sameAs 2891718801 @default.
• W2891718801 citedByCount "43" @default.
• W2891718801 countsByYear W28917188012018 @default.
• W2891718801 countsByYear W28917188012019 @default.
• W2891718801 countsByYear W28917188012020 @default.
• W2891718801 countsByYear W28917188012021 @default.
• W2891718801 countsByYear W28917188012022 @default.
• W2891718801 countsByYear W28917188012023 @default.
• W2891718801 crossrefType "journal-article" @default.
• W2891718801 hasAuthorship W2891718801A5016376222 @default.
• W2891718801 hasAuthorship W2891718801A5019810821 @default.
• W2891718801 hasAuthorship W2891718801A5024767797 @default.
• W2891718801 hasAuthorship W2891718801A5028114716 @default.
• W2891718801 hasAuthorship W2891718801A5090342811 @default.
• W2891718801 hasBestOaLocation W28917188011 @default.
• W2891718801 hasConcept C146849305 @default.
• W2891718801 hasConcept C153180895 @default.
• W2891718801 hasConcept C154945302 @default.
• W2891718801 hasConcept C31972630 @default.
• W2891718801 hasConcept C41008148 @default.
• W2891718801 hasConcept C52102323 @default.
• W2891718801 hasConcept C79061980 @default.
• W2891718801 hasConcept C81363708 @default.
• W2891718801 hasConceptScore W2891718801C146849305 @default.
• W2891718801 hasConceptScore W2891718801C153180895 @default.
• W2891718801 hasConceptScore W2891718801C154945302 @default.
• W2891718801 hasConceptScore W2891718801C31972630 @default.
• W2891718801 hasConceptScore W2891718801C41008148 @default.
• W2891718801 hasConceptScore W2891718801C52102323 @default.
• W2891718801 hasConceptScore W2891718801C79061980 @default.
• W2891718801 hasConceptScore W2891718801C81363708 @default.
• W2891718801 hasFunder F4320335087 @default.
• W2891718801 hasIssue "4" @default.
• W2891718801 hasLocation W28917188011 @default.
• W2891718801 hasLocation W28917188012 @default.
• W2891718801 hasOpenAccess W2891718801 @default.
• W2891718801 hasPrimaryLocation W28917188011 @default.
• W2891718801 hasRelatedWork W2011792403 @default.
• W2891718801 hasRelatedWork W2043151189 @default.
• W2891718801 hasRelatedWork W2099272513 @default.
• W2891718801 hasRelatedWork W2333544554 @default.
• W2891718801 hasRelatedWork W2810954168 @default.
• W2891718801 hasRelatedWork W2914179169 @default.
• W2891718801 hasRelatedWork W3003695190 @default.
• W2891718801 hasRelatedWork W3004045746 @default.
• W2891718801 hasRelatedWork W3089173771 @default.

• next