arXiv:2511.14179v2 Announce Type: replace 
Abstract: Existing self-supervised contrastive learning methods for skeleton-based action recognition often process all skeleton regions uniformly, and adopt a first-in-first-out (FIFO) queue to store negative samples, which leads to motion information loss and non-optimal negative sample selection. To address these challenges, this paper proposes Dominance-Game Contrastive Learning network for skeleton-based action Recognition (DoGCLR), a self-supervised framework based on game theory. DoGCLR models the construction of positive and negative samples as a dynamic Dominance Game, where both sample types interact to reach an equilibrium that balances semantic preservation and discriminative strength. Specifically, a spatio-temporal dual weight localization mechanism identifies key motion regions and guides region-wise augmentations to enhance motion diversity while maintaining semantics. In parallel, an entropy-driven dominance strategy manages the memory bank by retaining high entropy (hard) negatives and replacing low-entropy (weak) ones, ensuring consistent exposure to informative contrastive signals. Extensive experiments are conducted on NTU RGB+D and PKU-MMD datasets. On NTU RGB+D 60 X-Sub/X-View, DoGCLR achieves 81.1%/89.4% accuracy, and on NTU RGB+D 120 X-Sub/X-Set, DoGCLR achieves 71.2%/75.5% accuracy, surpassing state-of-the-art methods by 0.1%, 2.7%, 1.1%, and 2.3%, respectively. On PKU-MMD Part I/Part II, DoGCLR performs comparably to the state-of-the-art methods and achieves a 1.9% higher accuracy on Part II, highlighting its strong robustness on more challenging scenarios.

تقدم الورقة شبكة التعلم التبايني بلعبة الهيمنة (DoGCLR) للتعرف على الأفعال المعتمدة على الهيكل العظمي. تتناول القيود الموجودة في طرق التعلم التبايني الذاتي الإشراف، التي غالبًا ما تعالج جميع مناطق الهيكل العظمي بشكل موحد وتستخدم قوائم الانتظار FIFO لعينة سلبية، مما يؤدي إلى فقدان المعلومات. يستخدم DoGCLR نظرية الألعاب لإنشاء لعبة هيمنة ديناميكية لتفاعل العينات، مما يعزز تنوع الحركة مع الحفاظ على الدلالات من خلال آلية تحديد المواقع ذات الوزن المزدوج الزمني والمكاني.

El artículo presenta la Red de Aprendizaje Contrastivo por Juego de Dominancia (DoGCLR) para el reconocimiento de acciones basado en esqueletos. Aborda las limitaciones de los métodos de aprendizaje contrastivo auto-supervisado existentes, que a menudo tratan todas las regiones esqueléticas de manera uniforme y utilizan colas FIFO para muestras negativas, lo que lleva a la pérdida de información. DoGCLR emplea la teoría de juegos para crear un juego de dominancia dinámico para la interacción de muestras, mejorando la diversidad del movimiento mientras se preserva la semántica mediante un mecan…

Cet article présente le réseau de contraste d'apprentissage par jeu de dominance (DoGCLR) pour la reconnaissance d'actions basée sur des squelettes. Il aborde les limitations des méthodes d'apprentissage contrastif auto-supervisé existantes, qui traitent souvent toutes les régions squelettiques de manière uniforme et utilisent des files d'attente FIFO pour les échantillons négatifs, entraînant une perte d'information. DoGCLR utilise la théorie des jeux pour créer un jeu de dominance dynamique pour l'interaction des échantillons, améliorant la diversité des mouvements tout en préservant la séma…

The paper presents the Dominance-Game Contrastive Learning Network (DoGCLR) for skeleton-based action recognition. It addresses limitations in existing self-supervised contrastive learning methods, which often treat all skeleton regions uniformly and use FIFO queues for negative samples, leading to information loss. DoGCLR employs game theory to create a dynamic dominance game for sample interaction, enhancing motion diversity while preserving semantics through a spatio-temporal dual weight localization mechanism.

DoGCLR: Dominance-Game Contrastive Learning Network for Skeleton-Based Action Recognition

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.

DoGCLR: Dominance-Game Contrastive Learning Network for Skeleton-Based Action Recognition

Was this article worth reading? Share it

ZeroGPT.org

devActivity

ChurnDog