AIMC Topic: Attention

Clear Filters Showing 481 to 490 of 575 articles

Attention modeled as information in learning multisensory integration.

Neural networks : the official journal of the International Neural Network Society
Top-down cognitive processes affect the way bottom-up cross-sensory stimuli are integrated. In this paper, we therefore extend a successful previous neural network model of learning multisensory integration in the superior colliculus (SC) by top-down...

Attentional Enhancement of Auditory Mismatch Responses: a DCM/MEG Study.

Cerebral cortex (New York, N.Y. : 1991)
Despite similar behavioral effects, attention and expectation influence evoked responses differently: Attention typically enhances event-related responses, whereas expectation reduces them. This dissociation has been reconciled under predictive codin...

Enhancing realism in LiDAR scene generation with CSPA-DFN and linear cross-attention via Diffusion Transformer model.

Neural networks : the official journal of the International Neural Network Society
Point cloud diffusion models have found extensive applications in autonomous driving and robotics. However, there is still a big gap between their generated LiDAR scene samples and real-world data in terms of visual quality. This discrepancy primaril...

Artificial intelligence automated solution for hazard annotation and eye tracking in a simulated environment.

Accident; analysis and prevention
High-fidelity simulators and sensors are commonly used in research to create immersive environments for studying real-world problems. This setup records detailed data, generating large datasets. In driving research, a full-scale car model repurposed ...

A novel STA-EEGNet combined with channel selection for classification of EEG evoked in 2D and 3D virtual reality.

Medical engineering & physics
Virtual reality (VR), particularly through 3D presentations, significantly boosts user engagement and task efficiency in fields such as gaming, education, and healthcare, offering more immersive and interactive experiences than traditional 2D formats...

Multi-level semantic-aware transformer for image captioning.

Neural networks : the official journal of the International Neural Network Society
Effective visual representation is crucial for image captioning task. Among the existing methods, the grid-based visual encoding methods take fragmented features extracted from the entire image as input, lacking the fine-grained semantic information ...

Semantic information-based attention mapping network for few-shot knowledge graph completion.

Neural networks : the official journal of the International Neural Network Society
Few-shot Knowledge Graph Completion (FKGC), an emerging technology capable of inferring new triples using only a few reference relation triples, has gained significant attention in recent years. However, existing FKGC methods primarily focus on struc...

CFI-Former: Efficient lane detection by multi-granularity perceptual query attention transformer.

Neural networks : the official journal of the International Neural Network Society
Benefiting from the booming development of Transformer methods, the performance of lane detection tasks has been rapidly improved. However, due to the influence of inaccurate lane line shape constraints, the query sequences of existing transformer-ba...

A spatial-spectral fusion convolutional transformer network with contextual multi-head self-attention for hyperspectral image classification.

Neural networks : the official journal of the International Neural Network Society
Convolutional neural networks (CNNs) can effectively extract local features, while Vision Transformer excels at capturing global features. Combining these two networks to enhance the classification performance of hyperspectral images (HSI) has garner...

Self-attention fusion and adaptive continual updating for multimodal federated learning with heterogeneous data.

Neural networks : the official journal of the International Neural Network Society
Federated learning (FL) enables collaborative model training without direct data sharing, facilitating knowledge exchange while ensuring data privacy. Multimodal federated learning (MFL) is particularly advantageous for decentralized multimodal data,...