arXiv:2511.16860v1 Announce Type: new 
Abstract: Skeleton action recognition involves recognizing human action from human skeletons. The use of graph convolutional networks (GCNs) has driven major advances in this recognition task. In real-world scenarios, the captured skeletons are not always perfect or complete because of occlusions of parts of the human body or poor communication quality, leading to missing parts in skeletons or videos with missing frames. In the presence of such non-idealities, existing GCN models perform poorly due to missing local context. To address this limitation, we propose Parts-Mamba, a hybrid GCN-Mamba model designed to enhance the ability to capture and maintain contextual information from distant joints. The proposed Parts-Mamba model effectively captures part-specific information through its parts-specific scanning feature and preserves non-neighboring joint context via a parts-body fusion module. Our proposed model is evaluated on the NTU RGB+D 60 and NTU RGB+D 120 datasets under different occlusion settings, achieving up to 12.9% improvement in accuracy.

تم تقديم نموذج Parts-Mamba لتحسين التعرف على حركات الهيكل العظمي من خلال معالجة القيود التي تواجه الشبكات التلافيفية الرسومية (GCNs) الموجودة في السيناريوهات التي تحتوي على هياكل عظمية بشرية محجوبة. يقوم هذا النموذج الهجين بالتقاط معلومات محددة للأجزاء والحفاظ على الوعي السياقي من المفاصل البعيدة، مما يحسن دقة التعرف في التطبيقات الواقعية.

Se ha presentado el modelo Parts-Mamba para mejorar el reconocimiento de acciones esqueléticas al abordar las limitaciones de las redes de convolución gráfica (GCN) existentes en escenarios con esqueletos humanos ocluidos. Este modelo híbrido captura información específica de las partes y mantiene la conciencia contextual de las articulaciones distantes, mejorando así la precisión del reconocimiento en aplicaciones del mundo real.

Le modèle Parts-Mamba a été introduit pour améliorer la reconnaissance des actions squelettiques en abordant les limitations des réseaux de convolution graphique (GCN) existants dans des scénarios avec des squelettes humains occlus. Ce modèle hybride capture des informations spécifiques aux parties et maintient la conscience contextuelle des articulations éloignées, améliorant ainsi la précision de la reconnaissance dans des applications réelles.

The Parts-Mamba model has been introduced to enhance skeleton action recognition by addressing the limitations of existing graph convolutional networks (GCNs) in scenarios with occluded human skeletons. This hybrid model captures part-specific information and maintains contextual awareness from distant joints, improving recognition accuracy in real-world applications.

Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton

arXiv:2511.22433v2 Announce Type: replace 
Abstract: Recent advances in skeleton-based action recognition increasingly leverage semantic priors from Large Language Models (LLMs) to enrich skeletal representations. However, the LLM is typically queried in isolation from the recognition model and receives no performance feedback. As a result, it often fails to deliver the targeted discriminative cues critical to distinguish similar actions. To overcome these limitations, we propose SkeletonAgent, a novel framework that bridges the recognition model and the LLM through two cooperative agents, i.e., Questioner and Selector. Specifically, the Questioner identifies the most frequently confused classes and supplies them to the LLM as context for more targeted guidance. Conversely, the Selector parses the LLM's response to extract precise joint-level constraints and feeds them back to the recognizer, enabling finer-grained cross-modal alignment. Comprehensive evaluations on five benchmarks, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, FineGYM, and UAV-Human, demonstrate that SkeletonAgent consistently outperforms state-of-the-art benchmark methods. The code is available at https://github.com/firework8/SkeletonAgent.

تم تقديم إطار SkeletonAgent لتحسين التعرف على الأفعال المعتمد على الهياكل العظمية من خلال دمج نماذج اللغة الكبيرة (LLMs) مع نموذج التعرف عبر وكيلين تعاونيين، وهما السائل والمحدد. تهدف هذه الطريقة المبتكرة إلى تحسين دقة التمييز بين الأفعال المتشابهة من خلال تقديم إرشادات مستهدفة وتغذية راجعة بين LLM ونموذج التعرف.

Se ha presentado el marco SkeletonAgent para mejorar el reconocimiento de acciones basado en esqueletos, integrando Modelos de Lenguaje de Gran Tamaño (LLMs) con un modelo de reconocimiento a través de dos agentes cooperativos, el Cuestionador y el Selector. Este enfoque innovador busca mejorar la precisión en la distinción de acciones similares al proporcionar orientación y retroalimentación específicas entre el LLM y el modelo de reconocimiento.

Le cadre SkeletonAgent a été introduit pour améliorer la reconnaissance d'actions basée sur des squelettes en intégrant des modèles de langage de grande taille (LLMs) avec un modèle de reconnaissance à travers deux agents coopératifs, le Questionneur et le Sélecteur. Cette approche innovante vise à améliorer la précision de la distinction entre des actions similaires en fournissant des conseils ciblés et des retours d'information entre le LLM et le modèle de reconnaissance.

The SkeletonAgent framework has been introduced to enhance skeleton-based action recognition by integrating Large Language Models (LLMs) with a recognition model through two cooperative agents, the Questioner and Selector. This innovative approach aims to improve the accuracy of distinguishing similar actions by providing targeted guidance and feedback between the LLM and the recognition model.

Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton

Was this article worth reading? Share it

Grubby.AI

SnapChip

Fakeface