{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:35:29Z","timestamp":1761176129404,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Graph Convolutional Networks (GCNS) have been widely used with excellent performance in skeleton based human action recognition. In GCN-based methods, neighborhood graphs with semantics are important for the network, however, existing methods have limitations: although they optimise the neighborhood matrix by adaptive weighting, it is difficult to focus on key regions with high contribution to the action, resulting in a limited ability to discriminate visually similar actions. To solve this problem, we propose two approaches: 1) construct additional dynamic sensitive topology focusing on the spatial associations of key nodes by extracting the high contribution vertex set based on the magnitude of motion changes. 2) propose a regional-level spatio-temporal aggregation module to achieve fine-grained spatio-temporal semantic modeling. Finally, we validate the effectiveness of our proposed module through various comparative experiments.<\/jats:p>","DOI":"10.3233\/faia250853","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:44:01Z","timestamp":1761126241000},"source":"Crossref","is-referenced-by-count":0,"title":["Significance-Driven Skeleton Map Convolution for Skeleton-Based Action Recognition"],"prefix":"10.3233","author":[{"given":"Nuo","family":"Chen","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqun","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotao","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:44:01Z","timestamp":1761126241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250853","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}