AIMC Topic: Visual Perception

Clear Filters Showing 321 to 330 of 377 articles

Learning to manipulate and categorize in human and artificial agents.

Cognitive science
This study investigates the acquisition of integrated object manipulation and categorization abilities through a series of experiments in which human adults and artificial agents were asked to learn to manipulate two-dimensional objects that varied i...

Transfer learning for visual categorization: a survey.

IEEE transactions on neural networks and learning systems
Regular machine learning and data mining techniques study the training data for future inferences under a major assumption that the future data are within the same feature space or have the same distribution as the training data. However, due to the ...

Encoding of Numerosity With Robustness to Object and Scene Identity in Biologically Inspired Object Recognition Networks.

Neural computation
Number sense, the ability to rapidly estimate object quantities in a visual scene without precise counting, is a crucial cognitive capacity found in humans and many other animals. Recent studies have identified artificial neurons tuned to numbers of ...

Visual reasoning in object-centric deep neural networks: A comparative cognition approach.

Neural networks : the official journal of the International Neural Network Society
Achieving visual reasoning is a long-term goal of artificial intelligence. In the last decade, several studies have applied deep neural networks (DNNs) to the task of learning visual relations from images, with modest results in terms of generalizati...

Maintaining visual stability in naturalistic scenes: The roles of trans-saccadic memory and default assumptions.

Cognition
How is visual stability maintained across saccades? One theory poses the visual system has an underlying assumption that the visual world has not changed during the saccade, and scrutinization of trans-saccadic memory occurs only when there is strong...

Peripersonal and extrapersonal space encoding in virtual reality: Insights from an fMRI study.

NeuroImage
The brain processes objects in reachable peripersonal space and non-reachable extrapersonal space in different neural networks. In contrast to extrapersonal space, spatial processing in peripersonal space is linked to the activation of affordances in...

Ensuring SOTIF: Enhanced object detection techniques for autonomous driving.

Accident; analysis and prevention
Neural networks' insufficient interpretability can lead to unguaranteed Safety of the Intended Functionality (SOTIF) issues when perceptual results are not always met in autonomous driving applications. To address the safety shortcomings in the curre...

Distinct processing stages of cross-modal conflict in schizophrenia: The role of auditory cortex underactivation.

Schizophrenia research
BACKGROUND: The cross-modal conflict deficit is a key feature of schizophrenia. However, it remains largely unknown whether cross-modal conflict in schizophrenia diverges at distinct processing stages and its potential association with the auditory c...

Human visual perception-inspired medical image segmentation network with multi-feature compression.

Artificial intelligence in medicine
Medical image segmentation is crucial for computer-aided diagnosis and treatment planning, directly influencing clinical decision-making. To enhance segmentation accuracy, existing methods typically fuse local, global, and various other features. How...

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...