AIMC Topic: Pattern Recognition, Visual

Clear Filters Showing 51 to 60 of 152 articles

Depth in convolutional neural networks solves scene segmentation.

PLoS computational biology
Feed-forward deep convolutional neural networks (DCNNs) are, under specific conditions, matching and even surpassing human performance in object recognition in natural scenes. This performance suggests that the analysis of a loose collection of image...

Capsule networks as recurrent models of grouping and segmentation.

PLoS computational biology
Classically, visual processing is described as a cascade of local feedforward computations. Feedforward Convolutional Neural Networks (ffCNNs) have shown how powerful such models can be. However, using visual crowding as a well-controlled challenge, ...

Behavioral Activity Recognition Based on Gaze Ethograms.

International journal of neural systems
Noninvasive behavior observation techniques allow more natural human behavior assessment experiments with higher ecological validity. We propose the use of gaze ethograms in the context of user interaction with a computer display to characterize the ...

The interplay between multisensory integration and perceptual decision making.

NeuroImage
Facing perceptual uncertainty, the brain combines information from different senses to make optimal perceptual decisions and to guide behavior. However, decision making has been investigated mostly in unimodal contexts. Thus, how the brain integrates...

Local features and global shape information in object classification by deep convolutional neural networks.

Vision research
Deep convolutional neural networks (DCNNs) show impressive similarities to the human visual system. Recent research, however, suggests that DCNNs have limitations in recognizing objects by their shape. We tested the hypothesis that DCNNs are sensitiv...

Crowding in humans is unlike that in convolutional neural networks.

Neural networks : the official journal of the International Neural Network Society
Object recognition is a primary function of the human visual system. It has recently been claimed that the highly successful ability to recognise objects in a set of emergent computer vision systems-Deep Convolutional Neural Networks (DCNNs)-can form...

CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks.

Sensors (Basel, Switzerland)
Mobile devices such as sensors are used to connect to the Internet and provide services to users. Web services are vulnerable to automated attacks, which can restrict mobile devices from accessing websites. To prevent such automated attacks, CAPTCHAs...

Efficient inverse graphics in biological face processing.

Science advances
Vision not only detects and recognizes objects, but performs rich inferences about the underlying scene structure that causes the patterns of light we see. Inverting generative models, or "analysis-by-synthesis", presents a possible solution, but its...

Decoding dynamic affective responses to naturalistic videos with shared neural patterns.

NeuroImage
This study explored the feasibility of using shared neural patterns from brief affective episodes (viewing affective pictures) to decode extended, dynamic affective sequences in a naturalistic experience (watching movie-trailers). Twenty-eight partic...

Separability and geometry of object manifolds in deep neural networks.

Nature communications
Stimuli are represented in the brain by the collective population responses of sensory neurons, and an object presented under varying conditions gives rise to a collection of neural population responses called an 'object manifold'. Changes in the obj...