{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1901"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1901","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Hybrid architecture for human action recognition using skeleton data","abstract":"In this work, we propose a deep learning architecture, incorporating a Graph Convolutional Network (GCN) backbone combined with a partitioning transformer, that achieves results comparable to the state-of-the-art methods in skeleton based multi-person, multiview human action recognition. By leveraging attention-based GCN, the model captures context-dependent intrinsic topology while enhancing discriminative information. Furthermore, utilizing transformers, we harness their ability to aggregate long-range temporal information, allowing us to learn complex actions by attending to both short-term and long-term temporal windows. This is achieved through our partitioning strategy, which efficiently captures the relationships between neighboring and distant joints, enabling a comprehensive understanding of human movement dynamics. In this work, we also introduce a Cosine-based noise as a new data augmentation strategy for joints across time. This helps our model, Hybrid-Graformer, achieve accuracy comparable to the state-of-the-art across various skeleton-based action recognition benchmarks.","abstract_html":"In this work, we propose a deep learning architecture, incorporating a Graph Convolutional Network (GCN) backbone combined with a partitioning transformer, that achieves results comparable to the state-of-the-art methods in skeleton based multi-person, multiview human action recognition. By leveraging attention-based GCN, the model captures context-dependent intrinsic topology while enhancing discriminative information. Furthermore, utilizing transformers, we harness their ability to aggregate long-range temporal information, allowing us to learn complex actions by attending to both short-term and long-term temporal windows. This is achieved through our partitioning strategy, which efficiently captures the relationships between neighboring and distant joints, enabling a comprehensive understanding of human movement dynamics. In this work, we also introduce a Cosine-based noise as a new data augmentation strategy for joints across time. This helps our model, Hybrid-Graformer, achieve accuracy comparable to the state-of-the-art across various skeleton-based action recognition benchmarks.","abstract_has_math":false,"creators":["Nadeem, Muhammad Salik"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Qureshi, Faisal"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-12-01","date_published":"2024-12-01","updated_at":"2026-07-24T05:35:28Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1901","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Qureshi, Faisal"]},{"key":"dc:creator","label":"Author","values":["Nadeem, Muhammad Salik"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-03-18T19:03:06Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-03-18T19:03:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-12-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/1901"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this work, we propose a deep learning architecture, incorporating a Graph Convolutional Network (GCN) backbone combined with a partitioning transformer, that achieves results comparable to the state-of-the-art methods in skeleton based multi-person, multiview human action recognition. By leveraging attention-based GCN, the model captures context-dependent intrinsic topology while enhancing discriminative information. Furthermore, utilizing transformers, we harness their ability to aggregate long-range temporal information, allowing us to learn complex actions by attending to both short-term and long-term temporal windows. This is achieved through our partitioning strategy, which efficiently captures the relationships between neighboring and distant joints, enabling a comprehensive understanding of human movement dynamics. In this work, we also introduce a Cosine-based noise as a new data augmentation strategy for joints across time. This helps our model, Hybrid-Graformer, achieve accuracy comparable to the state-of-the-art across various skeleton-based action recognition benchmarks."]},{"key":"dc:title","label":"Title","values":["Hybrid architecture for human action recognition using skeleton data"]}]}],"canonical_facts":{"dc:contributor.advisor":["Qureshi, Faisal"],"dc:creator":["Nadeem, Muhammad Salik"],"dc:date.accessioned":["2025-03-18T19:03:06Z"],"dc:date.available":["2025-03-18T19:03:06Z"],"dc:date.issued":["2024-12-01"],"dc:description.abstract":["In this work, we propose a deep learning architecture, incorporating a Graph Convolutional Network (GCN) backbone combined with a partitioning transformer, that achieves results comparable to the state-of-the-art methods in skeleton based multi-person, multiview human action recognition. By leveraging attention-based GCN, the model captures context-dependent intrinsic topology while enhancing discriminative information. Furthermore, utilizing transformers, we harness their ability to aggregate long-range temporal information, allowing us to learn complex actions by attending to both short-term and long-term temporal windows. This is achieved through our partitioning strategy, which efficiently captures the relationships between neighboring and distant joints, enabling a comprehensive understanding of human movement dynamics. In this work, we also introduce a Cosine-based noise as a new data augmentation strategy for joints across time. This helps our model, Hybrid-Graformer, achieve accuracy comparable to the state-of-the-art across various skeleton-based action recognition benchmarks."],"dc:identifier.uri":["https://hdl.handle.net/10155/1901"],"dc:language.iso":["en"],"dc:title":["Hybrid architecture for human action recognition using skeleton data"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:28Z"}