Results 61 to 70 of about 22,886 (195)

NeurAll: Towards a Unified Visual Perception Model for Automated Driving

Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc.
Chennupati, Sumanth, Hughes, Ciaran, Leang, Isabelle, Milz, Stefan, Rawashdeh, Samir, Sistu, Ganesh, Yogamani, Senthil   +6 more
core  

Cell Segmentation Beyond 2D—A Review of the State‐of‐the‐Art

Advanced Intelligent Discovery, EarlyView.
Cell segmentation underpins many biological image analysis tasks, yet most deep learning methods remain limited to 2D despite the inherently 3D nature of cellular processes. This review surveys segmentation approaches beyond 2D, comparing 2.5D and fully 3D methods, analyzing 31 models and 32 volumetric datasets, and introducing a unified reference ...
Fabian Schmeisser, Haseeb Muhammad, Junaid Younas, Gillian Lovell, Bianca Migliori, Andreas Dengel, Sheraz Ahmed   +6 more
wiley   +1 more source

Uncertainty‐Guided Selective Adaptation Enables Cross‐Platform Predictive Fluorescence Microscopy

Advanced Intelligent Discovery, EarlyView.
Deep learning models often fail when transferred to new microscopes. A novel framework overcomes this by selectively adapting the early layers governing low‐level image statistics, while freezing deep layers that encode morphology. This uncertainty‐guided approach enables robust, label‐free virtual staining across diverse systems, democratizing ...
Kai‐Wen K. Yang, Andrew Bai, Alexandra Bermudez, Yunqi Hong, Zoe Latham, Iris Sloan, Michael Liu, Vishrut Goyal, Cho‐Jui Hsieh, Neil Y. C. Lin   +9 more
wiley   +1 more source

VAE+DDPG: An Attention‐Enhanced Variational Autoencoder for Deep Reinforcement Learning‐Based Autonomous Navigation in Low‐Light Environments

Advanced Intelligent Systems, EarlyView.
Variational Autoencoder+Deep Deterministic Policy Gradient addresses low‐light failures of infrared depth sensing for indoor robot navigation. Stage 1 pretrains an attention‐enhanced Variational Autoencoder (Convolutional Block Attention Module+Feature Pyramid Network) to map dark depth frames to a well‐lit reconstruction, yielding a 128‐D latent code ...
Uiseok Lee, Chanhong Hwang, Hyunseok Kang, Yechan Park, Hangwoo Jin, Tuan Anh Nguyen, Eunmi Choi, Dugki Min   +7 more
wiley   +1 more source

Calibration‐Free Electromyography Motor Intent Decoding Using Large‐Scale Supervised Pretraining

Advanced Intelligent Systems, EarlyView.
Calibration‐free electromyography motor intent decoding is enabled through large‐scale supervised pretraining across heterogeneous datasets. A Spatially Aware Feature‐learning Transformer processes variable channel counts and electrode geometries, allowing transfer across users and recording setups. On a held‐out benchmark, fine‐tuned cross‐user models
Alexander E. Olsson, Nebojša Maleševic, Anders Björkman, Christian Antfolk   +3 more
wiley   +1 more source

Device‐Level Implementation of Reservoir Computing With Memristors

Advanced Intelligent Systems, EarlyView.
Reservoir computing (RC) is an emerging computing scheme that employs a reservoir and a single readout layer, which can be actualized in the nanoscale with memristors. As a comprehensive overview, the principles of RC and the switching mechanisms of memristors are discussed, followed by actual demonstrations of memristor‐based RC and the remaining ...
Sunbeom Park, Hyojung Kim, Ho Won Jang
wiley   +1 more source

EMG‐Driven Telemetry and Inference System for Fish: Pose Reconstruction and Flow Sensing

Advanced Intelligent Systems, EarlyView.
This work introduces an electromyography (EMG)‐driven telemetry framework that reconstructs body pose and infers hydrodynamic conditions in freely swimming fish. A custom 16‐channel archival system records intramuscular EMG, enabling deep‐learning models to decode joint kinematics, classify flow regimes, and reveal channel‐efficient sensing strategies.
Rahdar Hussain Afridi, Waqar Hussain Afridi, Muhammad Hamza, Ahsan Tanveer, Mingxin Wu, Xingwen Zheng, Liang Li, Guangming Xie   +7 more
wiley   +1 more source

Intelligent Operator‐Independent Flexibility in Robotic Non‐Destructive Evaluation

Advanced Intelligent Systems, EarlyView.
Non‐destructive evaluation of high‐value components remains a manufacturing bottleneck due to rigid robotic calibration and fixturing. This study presents a flexible, adaptable system integrating 3D vision and force‐position control with a collaborative KUKA LBR robot. The geometry‐agnostic system enables pose‐independent ultrasonic inspection, detects
Amine Hifi, Randika K. W. Vithanage, Shaun McKnight, Vedran Tunukovic, Ewan Nicolson, Rylan Gomes, Alastair Poole, Ehsan Mohseni, Stephen Gareth Pierce, Charles MacLoed, Tom O’Hare, Gavin Munro   +11 more
wiley   +1 more source

A Flexible and Energy‐Efficient Compute‐in‐Memory Accelerator for Kolmogorov–Arnold Networks

Advanced Intelligent Systems, EarlyView.
This article presents KA‐CIM, a compute‐in‐memory accelerator for Kolmogorov–Arnold Networks (KANs). It enables flexible and efficient computation of arbitrary nonlinear functions through cross‐layer co‐optimization from algorithm to device. KA‐CIM surpasses CPU, ASIC, VMM‐CIM, and prior KAN accelerators by 1–3 orders of magnitude in energy‐delay ...
Chirag Sudarshan, Oliver Artner, Paul‐Philipp Manea, Sebastian Siegel, Susanne Hoffmann‐Eifert, Regina Dittmann, John Paul Strachan   +6 more
wiley   +1 more source

Retinal Vessel Segmentation: A Comprehensive Review From Classical Methods to Deep Learning Advances (1982–2025)

Advanced Intelligent Systems, EarlyView.
Four decades of retinal vessel segmentation research (1982–2025) are synthesized, spanning classical image processing, machine learning, and deep learning paradigms. A meta‐analysis of 428 studies establishes a unified taxonomy and highlights performance trends, generalization capabilities, and clinical relevance.
Avinash Bansal, Jan Kubíček, Jana Bahrová, Alice Varyšová, Martin Augustýnek, Marek Penhaker, Juraj Timkovič   +6 more
wiley   +1 more source