---
title: "Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition"
authors:
  - "Talha Ilyas"
  - "Deval Mehta"
  - "Zongyuan Ge"
doi: "10.24963/ijcai.2026/138"
url: "https://ijcai.org/proceedings/2026/138"
pdf: "https://ijcai.org/proceedings/2026/0138.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1233-1242"
track: "Main Track"
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"
---

# Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition

Talha Ilyas, Deval Mehta, Zongyuan Ge

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1233-1242. DOI: [10.24963/ijcai.2026/138](https://doi.org/10.24963/ijcai.2026/138)

## 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.