Results 81 to 90 of about 1,373,967 (287)
Vision and Multi-modal Transformers
International audienceTransformers that rely on the self-attention mechanism to capture global dependencies have dominated in natural language modelling and their use in other domains, e.g. speech processing, has shown great potential.
Guinaudeau, Camille
core +1 more source
This study applies machine learning regression to predict chromium layer thickness in decorative trivalent chromium electroplating, using 441 experiments from laboratory‐scale (1L) and pilot‐scale (14L) setups. Tree‐based models, particularly CatBoost, outperformed linear regression by capturing nonlinear parameter interactions (R2$R^2$ up to 0.77 ...
Christoph Baumer +4 more
wiley +1 more source
Centralized Position Embeddings for Vision Transformers
Vision Transformers (ViTs) have achieved remarkable success across various vision tasks. However, ViTs inherently lack spatial inductive biases, necessitating explicit position embedding (PE) schemes.
Chanyong Shin +3 more
doaj +1 more source
Digitalizing electroplating requires both domain knowledge and interoperability. This work introduces PlatOn, a domain ontology for trivalent chromium plating and coating characterization, and a hybrid pipeline that aligns it to a mid‐level reference ontology by combining eight similarity metrics with language model reasoning. Expert‐validated mappings
Janik Harter +10 more
wiley +1 more source
The community‐driven Platform MaterialDigital Core Ontology (PMDco) 3.0 is introduced as a Basic Formal Ontology‐aligned semantic backbone for the processing–structure–properties paradigm in Materials Science and Engineering. Modular engineering, automated releases, and validation workflows are highlighted and key semantic patterns for materials ...
Markus Schilling +15 more
wiley +1 more source
This paper presents a comprehensive comparison between Vision Transformers and Convolutional Neural Networks for face recognition related tasks, including extensive experiments on the tasks of face identification and verification.
Marcos Rodrigo +2 more
doaj +1 more source
FreqDualNet: frequency-aware vision transformers for tumor segmentation [PDF]
Recent advances in deep learning models such as U-Net Transformer (UNETR) and Swin U-Net Transformer (SwinUNETR) have significantly improved tumor segmentation accuracy and local structural sensitivity in medical imaging.
Jungro Lee, Minhyeok Lee
doaj +2 more sources
Augmented Models of High-Frequency Transformers for SMPS [PDF]
The modeling of high-frequency transformers via augmented equivalent circuits is addressed. The augmented models are composed of a low-frequency equivalent and a supplemental element modeled via real rational fitting. They offer both high accuracy levels
Savi, Patrizia +3 more
core +1 more source
Residual adhesive after electrode loading in adhesive‐assisted resistance spot welding is quantified through a traceable experimental‐to‐digital workflow. Chromatic confocal topography provides calibrated surface‐height data, while OpenCV detects the electrode imprint and integrates adhesive height into comparable volume metrics.
Sung‐Min Wi, Jiangdong Zhao
wiley +1 more source
Learning visual prompts for guiding the attention of vision transformers [PDF]
Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are shown to guide the model to attend to a target region on the image. However,
Rezaei, Razieh +5 more
core

