arXiv:2511.15379v1 Announce Type: new 
Abstract: Understanding complex human activities demands the ability to decompose motion into fine-grained, semantic-aligned sub-actions. This motion grounding process is crucial for behavior analysis, embodied AI and virtual reality. Yet, most existing methods rely on dense supervision with predefined action classes, which are infeasible in open-vocabulary, real-world settings. In this paper, we propose ZOMG, a zero-shot, open-vocabulary framework that segments motion sequences into semantically meaningful sub-actions without requiring any annotations or fine-tuning. Technically, ZOMG integrates (1) language semantic partition, which leverages large language models to decompose instructions into ordered sub-action units, and (2) soft masking optimization, which learns instance-specific temporal masks to focus on frames critical to sub-actions, while maintaining intra-segment continuity and enforcing inter-segment separation, all without altering the pretrained encoder. Experiments on three motion-language datasets demonstrate state-of-the-art effectiveness and efficiency of motion grounding performance, outperforming prior methods by +8.7\% mAP on HumanML3D benchmark. Meanwhile, significant improvements also exist in downstream retrieval, establishing a new paradigm for annotation-free motion understanding.

تقدم الورقة ZOMG، وهو إطار عمل مفتوح بدون إشراف مصمم لتأصيل حركة الإنسان. هذه الطريقة المبتكرة تقسم تسلسلات الحركة إلى إجراءات فرعية ذات معنى دلالي دون الحاجة إلى أي تعليقات أو ضبط. من خلال استخدام تقسيم الدلالات اللغوية وتحسين التعتيم الناعم، يعزز ZOMG فهم الأنشطة البشرية المعقدة، وهو أمر أساسي لتحليل السلوك، والذكاء الاصطناعي المجسد، والواقع الافتراضي.

El artículo presenta ZOMG, un marco de vocabulario abierto sin supervisión, diseñado para la anclaje del movimiento humano. Este enfoque innovador segmenta las secuencias de movimiento en subacciones semánticamente significativas sin necesidad de anotaciones ni ajustes. Al utilizar la partición semántica del lenguaje y la optimización de enmascaramiento suave, ZOMG mejora la comprensión de actividades humanas complejas, lo cual es esencial para el análisis de comportamiento, la IA encarnada y la realidad virtual.

Cet article présente ZOMG, un cadre de vocabulaire ouvert sans apprentissage supervisé, conçu pour l'ancrage du mouvement humain. Cette approche innovante segmente les séquences de mouvement en sous-actions sémantiquement significatives sans nécessiter d'annotations ni de réglages. En utilisant la partition sémantique du langage et l'optimisation par masquage doux, ZOMG améliore la compréhension des activités humaines complexes, essentielle pour l'analyse comportementale, l'IA incarnée et la réalité virtuelle.

The paper presents ZOMG, a zero-shot, open-vocabulary framework designed for human motion grounding. This innovative approach segments motion sequences into semantically meaningful sub-actions without the need for annotations or fine-tuning. By utilizing language semantic partitioning and soft masking optimization, ZOMG enhances the understanding of complex human activities, which is essential for applications in behavior analysis, embodied AI, and virtual reality.

Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training

arXiv:2512.11654v1 Announce Type: new 
Abstract: The acquisition cost for large, annotated motion datasets remains a critical bottleneck for skeletal-based Human Activity Recognition (HAR). Although Text-to-Motion (T2M) generative models offer a compelling, scalable source of synthetic data, their training objectives, which emphasize general artistic motion, and dataset structures fundamentally differ from HAR's requirements for kinematically precise, class-discriminative actions. This disparity creates a significant domain gap, making generalist T2M models ill-equipped for generating motions suitable for HAR classifiers. To address this challenge, we propose KineMIC (Kinetic Mining In Context), a transfer learning framework for few-shot action synthesis. KineMIC adapts a T2M diffusion model to an HAR domain by hypothesizing that semantic correspondences in the text encoding space can provide soft supervision for kinematic distillation. We operationalize this via a kinetic mining strategy that leverages CLIP text embeddings to establish correspondences between sparse HAR labels and T2M source data. This process guides fine-tuning, transforming the generalist T2M backbone into a specialized few-shot Action-to-Motion generator. We validate KineMIC using HumanML3D as the source T2M dataset and a subset of NTU RGB+D 120 as the target HAR domain, randomly selecting just 10 samples per action class. Our approach generates significantly more coherent motions, providing a robust data augmentation source that delivers a +23.1% accuracy points improvement. Animated illustrations and supplementary materials are available at (https://lucazzola.github.io/publications/kinemic).

تم تقديم KineMIC (التعدين الحركي في السياق) كإطار للتعلم الانتقالي يهدف إلى تحسين تخليق الإجراءات القليلة العينات لتعرف النشاط البشري (HAR). يتناول هذا الإطار الفجوة الكبيرة بين نماذج النص إلى الحركة العامة ومتطلبات مصنفي HAR الدقيقة، من خلال الاستفادة من التطابقات الدلالية في مساحة ترميز النص من أجل التقطير الحركي.

KineMIC (Kinetic Mining In Context) se ha presentado como un marco de aprendizaje por transferencia destinado a mejorar la síntesis de acciones con pocos ejemplos para el reconocimiento de actividades humanas (HAR). Este marco aborda la significativa brecha de dominio entre los modelos generales de Texto-a-Movimiento (T2M) y los requisitos precisos de los clasificadores HAR, aprovechando las correspondencias semánticas en la codificación de texto para la destilación cinemática.

KineMIC (Kinetic Mining In Context) a été introduit comme un cadre d'apprentissage par transfert visant à améliorer la synthèse d'actions à faible échantillonnage pour la reconnaissance d'activités humaines (HAR). Ce cadre aborde l'écart de domaine significatif entre les modèles Text-to-Motion (T2M) généraux et les exigences précises des classificateurs HAR, en s'appuyant sur des correspondances sémantiques dans l'encodage textuel pour la distillation cinématique.

KineMIC (Kinetic Mining In Context) has been introduced as a transfer learning framework aimed at enhancing few-shot action synthesis for Human Activity Recognition (HAR). This framework addresses the significant domain gap between general Text-to-Motion (T2M) models and the precise requirements of HAR classifiers, leveraging semantic correspondences in text encoding for kinematic distillation.

Kinetic Mining in Context: Few-Shot Action Synthesis via Text-to-Motion Distillation

One More Thing in AI – Your Shortcut to AI Mastery

Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training

Was this article worth reading? Share it

One More Thing in AI

Humanize AI

GPTHumanizer

GPTHuman

Zemith-3bda3b

Postugc

Ready to build your own newsroom?