Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319452844> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4319452844 abstract "Most semi-supervised skeleton-based action recognition approaches aim to learn the skeleton action representations only at the joint level, but neglect the crucial motion characteristics at the coarser-grained body (e.g., limb, trunk) level that provide rich additional semantic information, though the number of labeled data is limited. In this work, we propose a novel Pyramid Self-attention Polymerization Learning (dubbed as PSP Learning) framework to jointly learn body-level, part-level, and joint-level action representations of joint and motion data containing abundant and complementary semantic information via contrastive learning covering coarse-to-fine granularity. Specifically, to complement semantic information from coarse to fine granularity in skeleton actions, we design a new Pyramid Polymerizing Attention (PPA) mechanism that firstly calculates the body-level attention map, part-level attention map, and joint-level attention map, as well as polymerizes these attention maps in a level-by-level way (i.e., from body level to part level, and further to joint level). Moreover, we present a new Coarse-to-fine Contrastive Loss (CCL) including body-level contrast loss, part-level contrast loss, and joint-level contrast loss to jointly measure the similarity between the body/part/joint-level contrasting features of joint and motion data. Finally, extensive experiments are conducted on the NTU RGB+D and North-Western UCLA datasets to demonstrate the competitive performance of the proposed PSP Learning in the semi-supervised skeleton-based action recognition task. The source codes of PSP Learning are publicly available at https://github.com/1xbq1/PSP-Learning." @default.
- W4319452844 created "2023-02-09" @default.
- W4319452844 creator A5040437528 @default.
- W4319452844 creator A5069327650 @default.
- W4319452844 date "2023-02-05" @default.
- W4319452844 modified "2023-09-27" @default.
- W4319452844 title "Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition" @default.
- W4319452844 doi "https://doi.org/10.48550/arxiv.2302.02327" @default.
- W4319452844 hasPublicationYear "2023" @default.
- W4319452844 type Work @default.
- W4319452844 citedByCount "0" @default.
- W4319452844 crossrefType "posted-content" @default.
- W4319452844 hasAuthorship W4319452844A5040437528 @default.
- W4319452844 hasAuthorship W4319452844A5069327650 @default.
- W4319452844 hasBestOaLocation W43194528441 @default.
- W4319452844 hasConcept C119857082 @default.
- W4319452844 hasConcept C127413603 @default.
- W4319452844 hasConcept C153180895 @default.
- W4319452844 hasConcept C154945302 @default.
- W4319452844 hasConcept C170154142 @default.
- W4319452844 hasConcept C18555067 @default.
- W4319452844 hasConcept C18969341 @default.
- W4319452844 hasConcept C199360897 @default.
- W4319452844 hasConcept C41008148 @default.
- W4319452844 hasConceptScore W4319452844C119857082 @default.
- W4319452844 hasConceptScore W4319452844C127413603 @default.
- W4319452844 hasConceptScore W4319452844C153180895 @default.
- W4319452844 hasConceptScore W4319452844C154945302 @default.
- W4319452844 hasConceptScore W4319452844C170154142 @default.
- W4319452844 hasConceptScore W4319452844C18555067 @default.
- W4319452844 hasConceptScore W4319452844C18969341 @default.
- W4319452844 hasConceptScore W4319452844C199360897 @default.
- W4319452844 hasConceptScore W4319452844C41008148 @default.
- W4319452844 hasLocation W43194528441 @default.
- W4319452844 hasOpenAccess W4319452844 @default.
- W4319452844 hasPrimaryLocation W43194528441 @default.
- W4319452844 hasRelatedWork W2030530201 @default.
- W4319452844 hasRelatedWork W2144724818 @default.
- W4319452844 hasRelatedWork W2167178440 @default.
- W4319452844 hasRelatedWork W2887712106 @default.
- W4319452844 hasRelatedWork W2946101226 @default.
- W4319452844 hasRelatedWork W2961085424 @default.
- W4319452844 hasRelatedWork W4286629047 @default.
- W4319452844 hasRelatedWork W4306321456 @default.
- W4319452844 hasRelatedWork W4306674287 @default.
- W4319452844 hasRelatedWork W4224009465 @default.
- W4319452844 isParatext "false" @default.
- W4319452844 isRetracted "false" @default.
- W4319452844 workType "article" @default.