AIMC Topic: Neural Networks, Computer

Clear Filters Showing 26491 to 26500 of 31376 articles

VKAD: A novel fault detection and isolation model for uncertainty-aware industrial processes.

Neural networks : the official journal of the International Neural Network Society
Fault detection and isolation (FDI) are essential for effective monitoring of industrial processes. Modern industrial processes involve dynamic systems characterized by complex, high-dimensional nonlinearities, posing significant challenges for accur...

Towards better text image machine translation with multimodal codebook and multi-stage training.

Neural networks : the official journal of the International Neural Network Society
As a widely-used machine translation task, text image machine translation (TIMT) aims to translate the source texts embedded in the image to target translations. However, studies in this aspect face two challenges: (1) constructed in a cascaded manne...

Heterogeneous graph neural networks enhance pressure estimation in water distribution networks.

Water research
Pressure estimation is crucial for efficient operation and management of water distribution networks (WDNs). However, it is often challenged by limited sensor observations. While graph neural networks (GNNs) have been used to improve hydraulic and wa...

SFPGCL: Specificity-preserving federated population graph contrastive learning for multi-site ASD identification using rs-fMRI data.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
Autism spectrum disorder (ASD) is a severe neurodevelopmental disorder that affects people's social communication and daily routine. Most existing imaging studies on ASD use single site resting-state functional magnetic resonance imaging (rs-fMRI) da...

ReactDiff: Latent Diffusion for Facial Reaction Generation.

Neural networks : the official journal of the International Neural Network Society
Given the audio-visual clip of the speaker, facial reaction generation aims to predict the listener's facial reactions. The challenge lies in capturing the relevance between video and audio while balancing appropriateness, realism, and diversity. Whi...

Emergence of human-like attention and distinct head clusters in self-supervised vision transformers: A comparative eye-tracking study.

Neural networks : the official journal of the International Neural Network Society
Visual attention models aim to predict human gaze behavior, yet traditional saliency models and deep gaze prediction networks face limitations. Saliency models rely on handcrafted low-level visual features, often failing to capture human gaze dynamic...

Adaptive Diversity Induced Reweighting for long-tailed classification.

Neural networks : the official journal of the International Neural Network Society
Real-world large-scale data often exhibit a long-tailed distribution, making a classifier difficult to generalize well on tail categories. A straightforward and effective approach to tackling this issue is reweighting. Traditionally, the weight of a ...

Dynamic Multi-scale Feature Integration Network for unsupervised MR-CT synthesis.

Neural networks : the official journal of the International Neural Network Society
Unsupervised MR-CT synthesis presents a significant opportunity to reduce radiation exposure from CT scans and lower costs by eliminating the need for both MR and CT imaging. However, many existing unsupervised methods face limitations in capturing d...

DiverseReID: Towards generalizable person re-identification via Dynamic Style Hallucination and decoupled domain experts.

Neural networks : the official journal of the International Neural Network Society
Person re-identification (re-ID) models often fail to generalize well when deployed to other camera networks with domain shift. A classical domain generalization (DG) solution is to enhance the diversity of source data so that a model can learn more ...

Enhancing image-based virtual try-on with Multi-Controlled Diffusion Models.

Neural networks : the official journal of the International Neural Network Society
Image-based virtual try-on technology digitally overlays clothing onto images of individuals, enabling users to preview how garments fit without physical trial, thus enhancing the online shopping experience. While current diffusion-based virtual try-...