Results 111 to 120 of about 987,911 (296)

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, Ilche Georgievski, Marco Aiello   +2 more
wiley   +1 more source

Gradient-Semantic Compensation for Incremental Semantic Segmentation

IEEE Transactions on Multimedia
Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most current methods fail to address catastrophic forgetting and background shift since they 1) treat all previous classes equally without considering different forgetting paces ...
Wei Cong, Yang Cong, Jiahua Dong 0001, Gan Sun, Henghui Ding   +4 more
openaire   +3 more sources

DRIVE‐SAFE: Data‐Driven Robustness and Informed Validation for Evolving Specifications via Formal Evaluation

Advanced Robotics Research, EarlyView.
DRIVE‐SAFE evaluates learning‐based, black‐box autonomous driving policies against evolving temporal safety requirements using Signal Temporal Logic robustness metrics. It aggregates distributional robustness measures with domain‐informed weights to guide iterative retraining.
Kristy Sakano, Jianyu An, Dinesh Manocha, Huan Xu   +3 more
wiley   +1 more source

Learning‐Based Soft Robotic Grasping: Recent Progress and Remaining Challenges

Advanced Robotics Research, EarlyView.
This review analyzes learning‐based soft robotic grasping from a pipeline‐oriented perspective, encompassing soft gripper design, multimodal sensing, and learning‐based planning and control. It surveys key neural network architectures and benchmark datasets and identifies critical challenges such as sim‐to‐real transfer, generalization, and continual ...
Arnab Majumder, Jelizaveta Konstantinova, Graham Deacon, Kaspar Althoefer   +3 more
wiley   +1 more source

Conventional video shot segmentation to semantic shot segmentation

, 2015
Video shot segmentation is a preliminary process used in video content analysis which requires for content description. Conventional shot segmentation techniques nourished with statistical approaches depend on chromatic distributions of video frames.
Abdullah, NA, Zainuddin, R, Ranathunga, L   +2 more
core  

Hierarchical Context Learning of object components for unsupervised semantic segmentation [PDF]

Unsupervised Semantic Segmentation (USS) aims to learn semantically rich and dense representations without relying on labels. Recent advances in self-supervised learning have demonstrated the potential of pretrained vision transformers to capture patch ...
Tuxworth, Gervase, Zhou, Jun, Zhang, Jue, Bao, Dong, Gao, Yongsheng   +4 more
core   +1 more source

3D medical volume segmentation using hybrid multiresolution statistical approaches [PDF]

, 2010
This article is available through the Brunel Open Access Publishing Fund. Copyright © 2010 S AlZu’bi and A Amira.3D volume segmentation is the process of partitioning voxels into 3D regions (subvolumes) that represent meaningful physical entities which ...
Alzubi, S, Amira, A, Shadi AlZu'bi, Abbes Amira   +3 more
core   +1 more source

Flexible Sensors for Robotics Tactile Perception: A Review

Advanced Robotics Research, EarlyView.
Flexible tactile sensing for robotics is reviewed through four interconnected dimensions. Physical mechanisms include piezoresistive, capacitive, piezoelectric, triboelectric, iontronic, and optical sensing. Structural design includes bioinspired, defect‐based, and MEMS‐based tactile systems.
Yu Song, Ying Chen, Yihao Chen, Xue Feng
wiley   +1 more source

Semantic Segmentation with Spreading Scribbles

Hand-annotating medical images with segmentation masks requires an immense amount of time and effort from clinical experts. Replacing full masks with a simpler annotating gesture can mitigate annotation costs. This can come in the form of a scribble, and leads to weakly supervised training scenarios.
Yeva Gabrielyan, Varduhi Yeghiazaryan, Irina Voiculescu   +2 more
openaire   +1 more source

Brain‐Computer Interface Training Fosters Perceptual Skills to Detect Errors

Advanced Science, EarlyView.
Accurate perception of visuomotor errors underpins motor precision and learning, yet conventional behavioral training fails to improve sensitivity to subtle errors. Real‐time EEG‐based brain‐computer interface feedback targeting the error positivity component enhances perceptual learning of small errors.
Deland H. Liu, Fumiaki Iwane, Minsu Zhang, Leonardo G. Cohen, José del R. Millán   +4 more
wiley   +1 more source