FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2981341885> ?p ?o ?g. }

• W2981341885 abstract "With the prevalence of accessible depth sensors, dynamic human body skeletons have attracted much attention as a robust modality for action recognition. Previous methods model skeletons based on RNN or CNN, which has limited expressive power for irregular skeleton joints. While graph convolutional networks (GCN) have been proposed to address irregular graph-structured data, the fundamental graph construction remains challenging. In this paper, we represent skeletons naturally on graphs, and propose a graph regression based GCN (GR-GCN) for skeleton-based action recognition, aiming to capture the spatio-temporal variation in the data. As the graph representation is crucial to graph convolution, we first propose graph regression to statistically learn the underlying graph from multiple observations. In particular, we provide spatio-temporal modeling of skeletons and pose an optimization problem on the graph structure over consecutive frames, which enforces the sparsity of the underlying graph for efficient representation. The optimized graph not only connects each joint to its neighboring joints in the same frame strongly or weakly, but also links with relevant joints in the previous and subsequent frames. We then feed the optimized graph into the GCN along with the coordinates of the skeleton sequence for feature learning, where we deploy high-order and fast Chebyshev approximation of spectral graph convolution. Further, we provide analysis of the variation characterization by the Chebyshev approximation. Experimental results validate the effectiveness of the proposed graph regression and show that the proposed GR-GCN achieves the state-of-the-art performance on the widely used NTU RGB+D, UT-Kinect and SYSU 3D datasets." @default.
• W2981341885 created "2019-11-01" @default.
• W2981341885 creator A5001396675 @default.
• W2981341885 creator A5003527952 @default.
• W2981341885 creator A5047528624 @default.
• W2981341885 creator A5059045087 @default.
• W2981341885 creator A5076848346 @default.
• W2981341885 date "2019-10-15" @default.
• W2981341885 modified "2023-09-30" @default.
• W2981341885 title "Optimized Skeleton-based Action Recognition via Sparsified Graph Regression" @default.
• W2981341885 cites W1501856433 @default.
• W2981341885 cites W1522734439 @default.
• W2981341885 cites W1944615693 @default.
• W2981341885 cites W1951194945 @default.
• W2981341885 cites W1980811840 @default.
• W2981341885 cites W2048821851 @default.
• W2981341885 cites W2052648922 @default.
• W2981341885 cites W2064675550 @default.
• W2981341885 cites W2101491865 @default.
• W2981341885 cites W2143267104 @default.
• W2981341885 cites W2144392304 @default.
• W2981341885 cites W2145546283 @default.
• W2981341885 cites W2157331557 @default.
• W2981341885 cites W2158787690 @default.
• W2981341885 cites W2172156083 @default.
• W2981341885 cites W2224196924 @default.
• W2981341885 cites W2309415944 @default.
• W2981341885 cites W2441438155 @default.
• W2981341885 cites W2442651457 @default.
• W2981341885 cites W2507009361 @default.
• W2981341885 cites W2510185399 @default.
• W2981341885 cites W2519711346 @default.
• W2981341885 cites W2519758495 @default.
• W2981341885 cites W2556685112 @default.
• W2981341885 cites W2593146028 @default.
• W2981341885 cites W2605659599 @default.
• W2981341885 cites W2612707971 @default.
• W2981341885 cites W2613570903 @default.
• W2981341885 cites W2716916105 @default.
• W2981341885 cites W2736995747 @default.
• W2981341885 cites W2778523960 @default.
• W2981341885 cites W2794956979 @default.
• W2981341885 cites W2963020213 @default.
• W2981341885 cites W2963312728 @default.
• W2981341885 cites W2963355447 @default.
• W2981341885 cites W2963370140 @default.
• W2981341885 cites W2963497309 @default.
• W2981341885 cites W2964216549 @default.
• W2981341885 cites W3098538019 @default.
• W2981341885 cites W4230005465 @default.
• W2981341885 doi "https://doi.org/10.1145/3343031.3351170" @default.
• W2981341885 hasPublicationYear "2019" @default.
• W2981341885 type Work @default.
• W2981341885 sameAs 2981341885 @default.
• W2981341885 citedByCount "114" @default.
• W2981341885 countsByYear W29813418852019 @default.
• W2981341885 countsByYear W29813418852020 @default.
• W2981341885 countsByYear W29813418852021 @default.
• W2981341885 countsByYear W29813418852022 @default.
• W2981341885 countsByYear W29813418852023 @default.
• W2981341885 crossrefType "proceedings-article" @default.
• W2981341885 hasAuthorship W2981341885A5001396675 @default.
• W2981341885 hasAuthorship W2981341885A5003527952 @default.
• W2981341885 hasAuthorship W2981341885A5047528624 @default.
• W2981341885 hasAuthorship W2981341885A5059045087 @default.
• W2981341885 hasAuthorship W2981341885A5076848346 @default.
• W2981341885 hasBestOaLocation W29813418852 @default.
• W2981341885 hasConcept C11413529 @default.
• W2981341885 hasConcept C132525143 @default.
• W2981341885 hasConcept C153180895 @default.
• W2981341885 hasConcept C154945302 @default.
• W2981341885 hasConcept C2777212361 @default.
• W2981341885 hasConcept C2987834672 @default.
• W2981341885 hasConcept C41008148 @default.
• W2981341885 hasConcept C59404180 @default.
• W2981341885 hasConcept C80444323 @default.
• W2981341885 hasConceptScore W2981341885C11413529 @default.
• W2981341885 hasConceptScore W2981341885C132525143 @default.
• W2981341885 hasConceptScore W2981341885C153180895 @default.
• W2981341885 hasConceptScore W2981341885C154945302 @default.
• W2981341885 hasConceptScore W2981341885C2777212361 @default.
• W2981341885 hasConceptScore W2981341885C2987834672 @default.
• W2981341885 hasConceptScore W2981341885C41008148 @default.
• W2981341885 hasConceptScore W2981341885C59404180 @default.
• W2981341885 hasConceptScore W2981341885C80444323 @default.
• W2981341885 hasFunder F4320334977 @default.
• W2981341885 hasLocation W29813418851 @default.
• W2981341885 hasLocation W29813418852 @default.
• W2981341885 hasOpenAccess W2981341885 @default.
• W2981341885 hasPrimaryLocation W29813418851 @default.
• W2981341885 hasRelatedWork W2292254049 @default.
• W2981341885 hasRelatedWork W2507989420 @default.
• W2981341885 hasRelatedWork W2546942002 @default.
• W2981341885 hasRelatedWork W2592385986 @default.
• W2981341885 hasRelatedWork W2743674619 @default.
• W2981341885 hasRelatedWork W2905846897 @default.
• W2981341885 hasRelatedWork W2941155331 @default.
• W2981341885 hasRelatedWork W2998168123 @default.
• W2981341885 hasRelatedWork W2999247481 @default.
• W2981341885 hasRelatedWork W4287995534 @default.

• next