AI Medical Compendium Journal:
Neural networks : the official journal of the International Neural Network Society

Showing 51 to 60 of 2842 articles

Improving transferability of adversarial examples via statistical attribution-based attacks.

Neural networks : the official journal of the International Neural Network Society
Adversarial attacks are significant in uncovering vulnerabilities and assessing the robustness of deep neural networks (DNNs), offering profound insights into their internal mechanisms. Feature-level attacks, a potent approach, craft adversarial exam...

Probabilistic memory auto-encoding network for abnormal behavior detection in surveillance video.

Neural networks : the official journal of the International Neural Network Society
Abnormal behavior detection in surveillance video, as one of the essential functions in the intelligent surveillance system, plays a vital role in anti-terrorism, maintaining stability, and ensuring social security. Aiming at the problem of extremely...

Towards zero-shot human-object interaction detection via vision-language integration.

Neural networks : the official journal of the International Neural Network Society
Human-object interaction (HOI) detection aims to locate human-object pairs and identify their interaction categories in images. Most existing methods primarily focus on supervised learning, which relies on extensive manual HOI annotations. Such heavy...

PanoGen++: Domain-adapted text-guided panoramic environment generation for vision-and-language navigation.

Neural networks : the official journal of the International Neural Network Society
Vision-and-language navigation (VLN) tasks require agents to navigate three-dimensional environments guided by natural language instructions, offering substantial potential for diverse applications. However, the scarcity of training data impedes prog...

FingerPoseNet: A finger-level multitask learning network with residual feature sharing for 3D hand pose estimation.

Neural networks : the official journal of the International Neural Network Society
Hand pose estimation approaches commonly rely on shared hand feature maps to regress the 3D locations of all hand joints. Subsequently, they struggle to enhance finger-level features which are invaluable in capturing joint-to-finger associations and ...

SHFormer: Dynamic spectral filtering convolutional neural network and high-pass kernel generation transformer for adaptive MRI reconstruction.

Neural networks : the official journal of the International Neural Network Society
Attention Mechanism (AM) selectively focuses on essential information for imaging tasks and captures relationships between regions from distant pixel neighborhoods to compute feature representations. Accelerated magnetic resonance image (MRI) reconst...

Exponential stability of infinite-dimensional impulsive stochastic systems with Poisson jumps under aperiodically intermittent control.

Neural networks : the official journal of the International Neural Network Society
This paper studies the problem of mean square exponential stability (ES) for a class of impulsive stochastic infinite-dimensional systems with Poisson jumps (ISIDSP) using aperiodically intermittent control (AIC). It provides a detailed analysis of i...

Attribute-guided feature fusion network with knowledge-inspired attention mechanism for multi-source remote sensing classification.

Neural networks : the official journal of the International Neural Network Society
Land use and land cover (LULC) classification is a popular research area in remote sensing. The information of single-modal data is insufficient for accurate classification, especially in complex scenes, while the complementarity of multi-modal data ...

Ternary spike-based neuromorphic signal processing system.

Neural networks : the official journal of the International Neural Network Society
Deep Neural Networks (DNNs) have been successfully implemented across various signal processing fields, resulting in significant enhancements in performance. However, DNNs generally require substantial computational resources, leading to significant ...

FedELR: When federated learning meets learning with noisy labels.

Neural networks : the official journal of the International Neural Network Society
Existing research on federated learning (FL) usually assumes that training labels are of high quality for each client, which is impractical in many real-world scenarios (e.g., noisy labels by crowd-sourced annotations), leading to dramatic performanc...