Saved in:
Bibliographic Details
Main Authors: Ilyas, Talha, Mehta, Deval, Ge, Zongyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.07140
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909025666334720
author Ilyas, Talha
Mehta, Deval
Ge, Zongyuan
author_facet Ilyas, Talha
Mehta, Deval
Ge, Zongyuan
contents Skeleton-based human activity recognition 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. Code: https://github.com/Mr-TalhaIlyas/REASON
format Preprint
id arxiv_https___arxiv_org_abs_2605_07140
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition
Ilyas, Talha
Mehta, Deval
Ge, Zongyuan
Computer Vision and Pattern Recognition
Artificial Intelligence
Skeleton-based human activity recognition 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. Code: https://github.com/Mr-TalhaIlyas/REASON
title Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.07140