{"type":"ScholarlyArticle","title":"Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition","authors":[{"name":"Talha Ilyas","slug":"talha-ilyas","given":"Talha","family":"Ilyas","affiliation":""},{"name":"Deval Mehta","slug":"deval-mehta","given":"Deval","family":"Mehta","affiliation":""},{"name":"Zongyuan Ge","slug":"zongyuan-ge","given":"Zongyuan","family":"Ge","affiliation":""}],"abstract":"Skeleton-based human activity recognition (HAR) has achieved strong empirical performance, yet most existing models remain black boxes and difficult to interpret. In this work, we introduce a neurosymbolic formulation of skeleton-based HAR that reframes action recognition as concept-driven first-order logical reasoning over motion primitives. Our framework bridges representation learning and symbolic inference by grounding first-order logic predicates in learnable spatial and temporal motion concepts. Specifically, we employ a standard spatio-temporal skeleton encoder to extract latent motion representations, which are then mapped to interpretable concept predicates via a spatio-temporal concept decoder that explicitly separates pose-centric and dynamics-centric abstractions. These concept predicates are composed through differentiable first-order logic layers, enabling the model to learn human-readable logical rules that govern action semantics. To impose semantic structure on the learned concepts, we align skeleton representations with LLM-derived descriptions of atomic motion primitives, establishing a shared conceptual space for perception and reasoning. Extensive experiments on NTU RGB+D 60/120 and NW-UCLA demonstrate that our approach achieves competitive recognition performance while providing explicit, interpretable explanations grounded in logical structure. Our results highlight neurosymbolic reasoning as an effective paradigm for interpretable spatio-temporal action understanding.","doi":"10.24963/ijcai.2026/138","url":"https://ijcai.org/proceedings/2026/138","pdf":"https://ijcai.org/proceedings/2026/0138.pdf","markdown":"https://ijcai.org/proceedings/2026/138.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/138","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":138,"pages":{"first":1233,"last":1242},"keywords":["Computer Vision: Action and behavior recognition","Computer Vision: Transparency, accountability, fairness and privacy","Computer Vision: Interpretability and transparency","Computer Vision: Vision, language and reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}