DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chi, Hyung-gun | ko |
dc.contributor.author | Ha, Myoung Hoon | ko |
dc.contributor.author | Chi, Seunggeun | ko |
dc.contributor.author | Lee, Sang Wan | ko |
dc.contributor.author | Huang, Qixing | ko |
dc.contributor.author | Ramani, Karthik | ko |
dc.date.accessioned | 2023-03-16T06:00:41Z | - |
dc.date.available | 2023-03-16T06:00:41Z | - |
dc.date.created | 2023-03-08 | - |
dc.date.issued | 2022-06 | - |
dc.identifier.citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.20154 - 20164 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/305637 | - |
dc.description.abstract | Human skeleton-based action recognition offers a valuable means to understand the intricacies of human behavior because it can handle the complex relationships between physical constraints and intention. Although several studies have focused on encoding a skeleton, less attention has been paid to embed this information into the latent representations of human action. InfoGCN proposes a learning framework for action recognition combining a novel learning objective and an encoding method. First, we design an information bottleneck-based learning objective to guide the model to learn informative but compact latent representations. To provide discriminative information for classifying action, we introduce attention-based graph convolution that captures the context-dependent intrinsic topology of human action. In addition, we present a multi-modal representation of the skeleton using the relative position of joints, designed to provide complementary spatial information for joints. InfoGCN(1) surpasses the known state-of-the-art on multiple skeleton-based action recognition benchmarks with the accuracy of 93.0% on NTU RGB+D 60 cross-subject split, 89.8% on NTU RGB+D 120 cross-subject split, and 97.0% on NW-UCLA. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | InfoGCN: Representation Learning for Human Skeleton-based Action Recognition | - |
dc.type | Conference | - |
dc.identifier.wosid | 000870783005095 | - |
dc.identifier.scopusid | 2-s2.0-85141491864 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 20154 | - |
dc.citation.endingpage | 20164 | - |
dc.citation.publicationname | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | New Orleans, LA | - |
dc.identifier.doi | 10.1109/CVPR52688.2022.01955 | - |
dc.contributor.localauthor | Lee, Sang Wan | - |
dc.contributor.nonIdAuthor | Chi, Hyung-gun | - |
dc.contributor.nonIdAuthor | Ha, Myoung Hoon | - |
dc.contributor.nonIdAuthor | Chi, Seunggeun | - |
dc.contributor.nonIdAuthor | Huang, Qixing | - |
dc.contributor.nonIdAuthor | Ramani, Karthik | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.