Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384261535> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4384261535 abstract "3D human pose estimation has been researched for decades with promising fruits. 3D human pose lifting is one of the promising research directions toward the task where both estimated pose and ground truth pose data are used for training. Existing pose lifting works mainly focus on improving the performance of estimated pose, but they usually underperform when testing on the ground truth pose data. We observe that the performance of the estimated pose can be easily improved by preparing good quality 2D pose, such as fine-tuning the 2D pose or using advanced 2D pose detectors. As such, we concentrate on improving the 3D human pose lifting via ground truth data for the future improvement of more quality estimated pose data. Towards this goal, a simple yet effective model called Global-local Adaptive Graph Convolutional Network (GLA-GCN) is proposed in this work. Our GLA-GCN globally models the spatiotemporal structure via a graph representation and backtraces local joint features for 3D human pose estimation via individually connected layers. To validate our model design, we conduct extensive experiments on three benchmark datasets: Human3.6M, HumanEva-I, and MPI-INF-3DHP. Experimental results show that our GLA-GCN implemented with ground truth 2D poses significantly outperforms state-of-the-art methods (e.g., up to around 3%, 17%, and 14% error reductions on Human3.6M, HumanEva-I, and MPI-INF-3DHP, respectively). GitHub: https://github.com/bruceyo/GLA-GCN." @default.
- W4384261535 created "2023-07-14" @default.
- W4384261535 creator A5002277899 @default.
- W4384261535 creator A5019707070 @default.
- W4384261535 creator A5027453740 @default.
- W4384261535 creator A5057489654 @default.
- W4384261535 creator A5069427748 @default.
- W4384261535 creator A5086801574 @default.
- W4384261535 date "2023-07-11" @default.
- W4384261535 modified "2023-10-18" @default.
- W4384261535 title "GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video" @default.
- W4384261535 doi "https://doi.org/10.48550/arxiv.2307.05853" @default.
- W4384261535 hasPublicationYear "2023" @default.
- W4384261535 type Work @default.
- W4384261535 citedByCount "0" @default.
- W4384261535 crossrefType "posted-content" @default.
- W4384261535 hasAuthorship W4384261535A5002277899 @default.
- W4384261535 hasAuthorship W4384261535A5019707070 @default.
- W4384261535 hasAuthorship W4384261535A5027453740 @default.
- W4384261535 hasAuthorship W4384261535A5057489654 @default.
- W4384261535 hasAuthorship W4384261535A5069427748 @default.
- W4384261535 hasAuthorship W4384261535A5086801574 @default.
- W4384261535 hasBestOaLocation W43842615351 @default.
- W4384261535 hasConcept C132525143 @default.
- W4384261535 hasConcept C13280743 @default.
- W4384261535 hasConcept C146849305 @default.
- W4384261535 hasConcept C153180895 @default.
- W4384261535 hasConcept C154945302 @default.
- W4384261535 hasConcept C185798385 @default.
- W4384261535 hasConcept C205649164 @default.
- W4384261535 hasConcept C31972630 @default.
- W4384261535 hasConcept C36613465 @default.
- W4384261535 hasConcept C41008148 @default.
- W4384261535 hasConcept C52102323 @default.
- W4384261535 hasConcept C65909025 @default.
- W4384261535 hasConcept C80444323 @default.
- W4384261535 hasConcept C81363708 @default.
- W4384261535 hasConceptScore W4384261535C132525143 @default.
- W4384261535 hasConceptScore W4384261535C13280743 @default.
- W4384261535 hasConceptScore W4384261535C146849305 @default.
- W4384261535 hasConceptScore W4384261535C153180895 @default.
- W4384261535 hasConceptScore W4384261535C154945302 @default.
- W4384261535 hasConceptScore W4384261535C185798385 @default.
- W4384261535 hasConceptScore W4384261535C205649164 @default.
- W4384261535 hasConceptScore W4384261535C31972630 @default.
- W4384261535 hasConceptScore W4384261535C36613465 @default.
- W4384261535 hasConceptScore W4384261535C41008148 @default.
- W4384261535 hasConceptScore W4384261535C52102323 @default.
- W4384261535 hasConceptScore W4384261535C65909025 @default.
- W4384261535 hasConceptScore W4384261535C80444323 @default.
- W4384261535 hasConceptScore W4384261535C81363708 @default.
- W4384261535 hasLocation W43842615351 @default.
- W4384261535 hasOpenAccess W4384261535 @default.
- W4384261535 hasPrimaryLocation W43842615351 @default.
- W4384261535 hasRelatedWork W1628937209 @default.
- W4384261535 hasRelatedWork W1798868054 @default.
- W4384261535 hasRelatedWork W1968716783 @default.
- W4384261535 hasRelatedWork W2004095265 @default.
- W4384261535 hasRelatedWork W2099272513 @default.
- W4384261535 hasRelatedWork W2129348295 @default.
- W4384261535 hasRelatedWork W2144760288 @default.
- W4384261535 hasRelatedWork W2891001608 @default.
- W4384261535 hasRelatedWork W3102636071 @default.
- W4384261535 hasRelatedWork W4312709684 @default.
- W4384261535 isParatext "false" @default.
- W4384261535 isRetracted "false" @default.
- W4384261535 workType "article" @default.