Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376166918> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4376166918 abstract "In human pose estimation methods based on graph convolutional architectures, the human skeleton is usually modeled as an undirected graph whose nodes are body joints and edges are connections between neighboring joints. However, most of these methods tend to focus on learning relationships between body joints of the skeleton using first-order neighbors, ignoring higher-order neighbors and hence limiting their ability to exploit relationships between distant joints. In this paper, we introduce a higher-order regular splitting graph network (RS-Net) for 2D-to-3D human pose estimation using matrix splitting in conjunction with weight and adjacency modulation. The core idea is to capture long-range dependencies between body joints using multi-hop neighborhoods and also to learn different modulation vectors for different body joints as well as a modulation matrix added to the adjacency matrix associated to the skeleton. This learnable modulation matrix helps adjust the graph structure by adding extra graph edges in an effort to learn additional connections between body joints. Instead of using a shared weight matrix for all neighboring body joints, the proposed RS-Net model applies weight unsharing before aggregating the feature vectors associated to the joints in order to capture the different relations between them. Experiments and ablations studies performed on two benchmark datasets demonstrate the effectiveness of our model, achieving superior performance over recent state-of-the-art methods for 3D human pose estimation." @default.
- W4376166918 created "2023-05-12" @default.
- W4376166918 creator A5025509195 @default.
- W4376166918 creator A5030269948 @default.
- W4376166918 date "2023-05-09" @default.
- W4376166918 modified "2023-10-14" @default.
- W4376166918 title "Regular Splitting Graph Network for 3D Human Pose Estimation" @default.
- W4376166918 doi "https://doi.org/10.48550/arxiv.2305.05785" @default.
- W4376166918 hasPublicationYear "2023" @default.
- W4376166918 type Work @default.
- W4376166918 citedByCount "0" @default.
- W4376166918 crossrefType "posted-content" @default.
- W4376166918 hasAuthorship W4376166918A5025509195 @default.
- W4376166918 hasAuthorship W4376166918A5030269948 @default.
- W4376166918 hasBestOaLocation W43761669181 @default.
- W4376166918 hasConcept C11413529 @default.
- W4376166918 hasConcept C114614502 @default.
- W4376166918 hasConcept C132525143 @default.
- W4376166918 hasConcept C153180895 @default.
- W4376166918 hasConcept C154945302 @default.
- W4376166918 hasConcept C180356752 @default.
- W4376166918 hasConcept C184720557 @default.
- W4376166918 hasConcept C33923547 @default.
- W4376166918 hasConcept C41008148 @default.
- W4376166918 hasConcept C52102323 @default.
- W4376166918 hasConcept C80444323 @default.
- W4376166918 hasConceptScore W4376166918C11413529 @default.
- W4376166918 hasConceptScore W4376166918C114614502 @default.
- W4376166918 hasConceptScore W4376166918C132525143 @default.
- W4376166918 hasConceptScore W4376166918C153180895 @default.
- W4376166918 hasConceptScore W4376166918C154945302 @default.
- W4376166918 hasConceptScore W4376166918C180356752 @default.
- W4376166918 hasConceptScore W4376166918C184720557 @default.
- W4376166918 hasConceptScore W4376166918C33923547 @default.
- W4376166918 hasConceptScore W4376166918C41008148 @default.
- W4376166918 hasConceptScore W4376166918C52102323 @default.
- W4376166918 hasConceptScore W4376166918C80444323 @default.
- W4376166918 hasLocation W43761669181 @default.
- W4376166918 hasOpenAccess W4376166918 @default.
- W4376166918 hasPrimaryLocation W43761669181 @default.
- W4376166918 hasRelatedWork W1461621550 @default.
- W4376166918 hasRelatedWork W2020350089 @default.
- W4376166918 hasRelatedWork W2034295284 @default.
- W4376166918 hasRelatedWork W2044000116 @default.
- W4376166918 hasRelatedWork W2155775419 @default.
- W4376166918 hasRelatedWork W2532886198 @default.
- W4376166918 hasRelatedWork W3164306936 @default.
- W4376166918 hasRelatedWork W3194558310 @default.
- W4376166918 hasRelatedWork W4287178724 @default.
- W4376166918 hasRelatedWork W62482549 @default.
- W4376166918 isParatext "false" @default.
- W4376166918 isRetracted "false" @default.
- W4376166918 workType "article" @default.