AIMC Topic: Attention

Clear Filters Showing 31 to 40 of 587 articles

A personalized recommendation algorithm for English exercises incorporating fuzzy cognitive models and multiple attention mechanisms.

Scientific reports
In the era of digital education, the rapid growth and disordered distribution of learning resources present new challenges for online learning. However, most of the exercise recommendation systems lack targeted guidance and personalization. In respon...

An Efficient Graph Learning System for Emotion Recognition Inspired by the Cognitive Prior Graph of EEG Brain Network.

IEEE transactions on neural networks and learning systems
Benefiting from the high-temporal resolution of electroencephalogram (EEG), EEG-based emotion recognition has become one of the hotspots of affective computing. For EEG-based emotion recognition systems, it is crucial to utilize state-of-the-art lear...

High-Performance Method and Architecture for Attention Computation in DNN Inference.

IEEE transactions on biomedical circuits and systems
In recent years, The combination of Attention mechanism and deep learning has a wide range of applications in the field of medical imaging. However, due to its complex computational processes, existing hardware architectures have high resource consum...

Placing Objects on Table Is Preferred over Direct Handovers When Users Are Occupied.

Sensors (Basel, Switzerland)
Service robots commonly deliver objects through direct handovers, assuming users are fully attentive. However, in real-world scenarios, users are often occupied with other tasks. This paper investigates how user attentiveness affects preferences betw...

A vision attention driven Language framework for medical report generation.

Scientific reports
This study introduces the Medical Vision Attention Generation (MedVAG) model, a novel framework designed to facilitate the automated generation of medical reports. MedVAG integrates Vision Transformer (ViT)-based visual feature extraction and GPT-2 l...

Using machine learning to simultaneously quantify multiple cognitive components of episodic memory.

Nature communications
Why do we remember some events but forget others? Previous studies attempting to decode successful vs. unsuccessful brain states to investigate this question have met with limited success, potentially due, in part, to assessing episodic memory as a u...

BSA-Seg: A Bi-level sparse attention network combining narrow band loss for multi-target medical image segmentation.

Neural networks : the official journal of the International Neural Network Society
Segmentation of multiple targets of varying sizes within medical images is of significant importance for the diagnosis of disease and pathological research. Transformer-based methods are emerging in the medical image segmentation, leveraging the powe...

AAPMatcher: Adaptive attention pruning matcher for accurate local feature matching.

Neural networks : the official journal of the International Neural Network Society
Local feature matching, which seeks to establish correspondences between two images, serves as a fundamental component in numerous computer vision applications, such as camera tracking and 3D mapping. Recently, Transformer has demonstrated remarkable...

Object Recognition Using Shape and Texture Tactile Information: A Fusion Network Based on Data Augmentation and Attention Mechanism.

IEEE transactions on haptics
Currently, most tactile-based object recognition algorithms focus on single shape or texture recognition. However, these single attribute-based recognition methods perform poorly when dealing with objects with similar shape or texture characteristics...

EEG detection and recognition model for epilepsy based on dual attention mechanism.

Scientific reports
In the field of clinical neurology, automated detection of epileptic seizures based on electroencephalogram (EEG) signals has the potential to significantly accelerate the diagnosis of epilepsy. This rapid and accurate diagnosis enables doctors to pr...