FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186796015> ?p ?o ?g. }

• W3186796015 abstract "Graph convolutional networks have significantly improved 3D human pose estimation by representing the human skeleton as an undirected graph. However, this representation fails to reflect the articulated characteristic of human skeletons as the hierarchical orders among the joints are not explicitly presented. In this paper, we propose to represent the human skeleton as a directed graph with the joints as nodes and bones as edges that are directed from parent joints to child joints. By so doing, the directions of edges can explicitly reflect the hierarchical relationships among the nodes. Based on this representation, we further propose a spatial-temporal conditional directed graph convolution to leverage varying non-local dependence for different poses by conditioning the graph topology on input poses. Altogether, we form a U-shaped network, named U-shaped Conditional Directed Graph Convolutional Network, for 3D human pose estimation from monocular videos. To evaluate the effectiveness of our method, we conducted extensive experiments on two challenging large-scale benchmarks: Human3.6M and MPI-INF-3DHP. Both quantitative and qualitative results show that our method achieves top performance. Also, ablation studies show that directed graphs can better exploit the hierarchy of articulated human skeletons than undirected graphs, and the conditional connections can yield adaptive graph topologies for different poses." @default.
• W3186796015 created "2021-08-02" @default.
• W3186796015 creator A5001992062 @default.
• W3186796015 creator A5017857966 @default.
• W3186796015 creator A5035842819 @default.
• W3186796015 creator A5064046791 @default.
• W3186796015 creator A5076127071 @default.
• W3186796015 date "2021-07-16" @default.
• W3186796015 modified "2023-09-23" @default.
• W3186796015 title "Conditional Directed Graph Convolution for 3D Human Pose Estimation" @default.
• W3186796015 cites W196761320 @default.
• W3186796015 cites W2064675550 @default.
• W3186796015 cites W2101032778 @default.
• W3186796015 cites W2116341502 @default.
• W3186796015 cites W2307770531 @default.
• W3186796015 cites W2404595106 @default.
• W3186796015 cites W2554247908 @default.
• W3186796015 cites W2583372902 @default.
• W3186796015 cites W2604375920 @default.
• W3186796015 cites W2606780347 @default.
• W3186796015 cites W2611932403 @default.
• W3186796015 cites W2612706635 @default.
• W3186796015 cites W2788865504 @default.
• W3186796015 cites W2797184202 @default.
• W3186796015 cites W2916798096 @default.
• W3186796015 cites W2948058585 @default.
• W3186796015 cites W2948246283 @default.
• W3186796015 cites W2962730651 @default.
• W3186796015 cites W2962896489 @default.
• W3186796015 cites W2963017945 @default.
• W3186796015 cites W2963076818 @default.
• W3186796015 cites W2963084622 @default.
• W3186796015 cites W2963592930 @default.
• W3186796015 cites W2963984147 @default.
• W3186796015 cites W2964016027 @default.
• W3186796015 cites W2964113829 @default.
• W3186796015 cites W2964221239 @default.
• W3186796015 cites W2964321699 @default.
• W3186796015 cites W2966735886 @default.
• W3186796015 cites W2970107519 @default.
• W3186796015 cites W2970285700 @default.
• W3186796015 cites W2970971581 @default.
• W3186796015 cites W2972662547 @default.
• W3186796015 cites W2982064756 @default.
• W3186796015 cites W2982085725 @default.
• W3186796015 cites W2983796203 @default.
• W3186796015 cites W2984313141 @default.
• W3186796015 cites W2988856441 @default.
• W3186796015 cites W2998027150 @default.
• W3186796015 cites W3009246422 @default.
• W3186796015 cites W3022928074 @default.
• W3186796015 cites W3034448411 @default.
• W3186796015 cites W3034482680 @default.
• W3186796015 cites W3034581612 @default.
• W3186796015 cites W3034971010 @default.
• W3186796015 cites W3036133893 @default.
• W3186796015 cites W3083132452 @default.
• W3186796015 cites W3097623574 @default.
• W3186796015 cites W3098473649 @default.
• W3186796015 cites W3098612954 @default.
• W3186796015 cites W3101560663 @default.
• W3186796015 cites W3106546328 @default.
• W3186796015 cites W3106838237 @default.
• W3186796015 cites W3106882556 @default.
• W3186796015 cites W3127588730 @default.
• W3186796015 cites W3145818495 @default.
• W3186796015 cites W4210257598 @default.
• W3186796015 doi "https://doi.org/10.48550/arxiv.2107.07797" @default.
• W3186796015 hasPublicationYear "2021" @default.
• W3186796015 type Work @default.
• W3186796015 sameAs 3186796015 @default.
• W3186796015 citedByCount "0" @default.
• W3186796015 crossrefType "posted-content" @default.
• W3186796015 hasAuthorship W3186796015A5001992062 @default.
• W3186796015 hasAuthorship W3186796015A5017857966 @default.
• W3186796015 hasAuthorship W3186796015A5035842819 @default.
• W3186796015 hasAuthorship W3186796015A5064046791 @default.
• W3186796015 hasAuthorship W3186796015A5076127071 @default.
• W3186796015 hasBestOaLocation W31867960151 @default.
• W3186796015 hasConcept C104317684 @default.
• W3186796015 hasConcept C11413529 @default.
• W3186796015 hasConcept C132525143 @default.
• W3186796015 hasConcept C146380142 @default.
• W3186796015 hasConcept C153083717 @default.
• W3186796015 hasConcept C153180895 @default.
• W3186796015 hasConcept C154945302 @default.
• W3186796015 hasConcept C157406716 @default.
• W3186796015 hasConcept C185592680 @default.
• W3186796015 hasConcept C203776342 @default.
• W3186796015 hasConcept C22149727 @default.
• W3186796015 hasConcept C41008148 @default.
• W3186796015 hasConcept C52102323 @default.
• W3186796015 hasConcept C55493867 @default.
• W3186796015 hasConcept C66746571 @default.
• W3186796015 hasConcept C80444323 @default.
• W3186796015 hasConceptScore W3186796015C104317684 @default.
• W3186796015 hasConceptScore W3186796015C11413529 @default.
• W3186796015 hasConceptScore W3186796015C132525143 @default.
• W3186796015 hasConceptScore W3186796015C146380142 @default.
• W3186796015 hasConceptScore W3186796015C153083717 @default.

• next