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

arXiv: https://arxiv.org/abs/2605.07140 · HTML: https://mlsanity.com/paper/2605.07140/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Cross-view Action Modeling, Learning and Recognition](https://mlsanity.com/paper/1405.2941/) (2014)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2208.10741/) (2022)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [Interpretable Neural-Symbolic Concept Reasoning](https://mlsanity.com/paper/2304.14068/) (2023)
- [Generative Action Description Prompts for Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.05318/) (2022)
- [LLMs are Good Action Recognizers](https://mlsanity.com/paper/2404.00532/) (2024)
- [SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition](https://mlsanity.com/paper/2209.02399/) (2022)
- [HAKE: A Knowledge Engine Foundation for Human Activity Understanding](https://mlsanity.com/paper/2202.06851/) (2022)
- [Understanding Video Transformers via Universal Concept Discovery](https://mlsanity.com/paper/2401.10831/) (2024)
- [Best of both worlds: local and global explanations with human-understandable concepts](https://mlsanity.com/paper/2106.08641/) (2021)
- [Learning Interpretable Rules for Scalable Data Representation and Classification](https://mlsanity.com/paper/2310.14336/) (2023)
- [Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment](https://mlsanity.com/paper/2403.13798/) (2024)
- [Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections](https://mlsanity.com/paper/2411.14796/) (2024)
- [Privacy-preserving Early Detection of Epileptic Seizures in Videos](https://mlsanity.com/paper/2309.08794/) (2023)
- [Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models](https://mlsanity.com/paper/2506.01334/) (2025)
- [LogicCBMs: Logic-Enhanced Concept-Based Learning](https://mlsanity.com/paper/2512.07383/) (2025)
- [Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models](https://mlsanity.com/paper/2503.02917/) (2025)
- [WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification](https://mlsanity.com/paper/2509.17740/) (2025)
- [SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition](https://mlsanity.com/paper/2511.10091/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Neurosymbolic Framework for Interpretable Skeleton-Based Seizure Detection via Concept-Driven Logical Reasoning](https://mlsanity.com/paper/2606.21252/) (2026)

## Abstract (arXiv)

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