CoRF-Yoga: Cross-Modal Contrastive Learning for Robust, Feasible Yoga Pose Recognition
IEEE AccessRecognizing yoga poses in real-world environments is challenging due to sensor-dependent noise, execution variability, and the high cost of large-scale manual annotation, which limits the scalability of existing supervised approaches.
Zolboo Damiran +4 more
doaj +1 more source
Multimodal Engagement Assessment in Children During Invented Story Paradigm With a Social Robot
Advanced Robotics Research, EarlyView.A multimodal framework is proposed to assess children's engagement during storytelling interactions with a social robot. Gaze, physiological, and behavioral data are combined and validated against observer ratings. An automated gaze‐labeling strategy is introduced, and supervised classifiers achieve high accuracy. The study supports scalable engagement
Laura Fiorini +7 more
wiley +1 more source
Multimodal Human–Robot Interaction Using Human Pose Estimation and Local Large Language Models
Advanced Robotics Research, EarlyView.A multimodal human–robot interaction framework integrates human pose estimation (HPE) and a large language model (LLM) for gesture‐ and voice‐based robot control. Speech‐to‐text (STT) enables voice command interpretation, while a safety‐aware arbitration mechanism prioritizes gesture input for rapid intervention.
Nasiru Aboki +2 more
wiley +1 more source
Uncovering the Redundancy in Graph Self-supervised Learning Models [PDF]
Graph self-supervised learning, as a powerful pre-training paradigm for Graph Neural Networks (GNNs) without labels, has received considerable attention.
Wang, X +5 more
core
MalSSL—Self-Supervised Learning for Accurate and Label-Efficient Malware Classification
IEEE AccessMalware classification with supervised learning requires a large dataset, which needs an expensive and time-consuming labeling process. In this paper, we explore the efficacy of self-supervised learning techniques for malware classification.
Setia Juli Irzal Ismail +4 more
doaj +1 more source
LLM‐Integrated Human–Robot Interaction System for Microrobots
Advanced Robotics Research, EarlyView.This paper proposes an LLM‐based control framework for guiding microrobots using human natural language. This framework can convert the natural human speech into safe and executable command sets for reliable navigation in complex environments. The experimental results show high accuracy and robustness in task performance, demonstrating the potential of
Bairong Zhu, Amar Salehi, Tingting Yu
wiley +1 more source
Towards generalisable foundation models for brain MRI
npj ImagingFoundation models trained with self-supervised learning are increasingly enabling scalable and generalisable solutions in medical imaging. However, most existing foundation models are designed for 2D natural images and do not explicitly leverage the ...
Moona Mazher +2 more
doaj +1 more source
Cross‐Scale Hierarchical Targeted Delivery System Based on Small‐Scale Magnetic Robots
Advanced Robotics Research, EarlyView.This article reviews a cross‐scale hierarchical targeted delivery system that integrates magnetic continuum robots and magnetic microrobots. By combining rapid long‐range navigation with precise microscale targeting, the system overcomes key limitations of single‐scale approaches.
Junjian Zhou +4 more
wiley +1 more source
Mutual Adaptation and Influence: Review of Latent Dynamics Models in Human–Robot Interaction
Advanced Robotics Research, EarlyView.Robots are becoming better teammates by learning hidden patterns in how people act. This review covers how state‐of‐the‐art approaches leverage these patterns to help robots not only react but also anticipate and guide cooperation. Here, we synthesize a unifying framework for these approaches, classify and review existing works, and highlight key ...
Mason O. Smith +4 more
wiley +1 more source
Self-supervised learning yields representational signatures of category-selective cortex. [PDF]
Commun BiolJanini D, Cichy R.
europepmc +2 more sources