A5047702194- Face Recognition and Perception
- Visual perception and processing mechanisms
- Multisensory perception and integration
- Neural dynamics and brain function
- Insect behavior and control techniques
- Date Palm Research Studies
- Spectroscopy and Chemometric Analyses
- Plant and animal studies
- Insect-Plant Interactions and Control
- Action Observation and Synchronization
- Industrial Vision Systems and Defect Detection
- Remote-Sensing Image Classification
- Forest Insect Ecology and Management
- Cell Image Analysis Techniques
- Primate Behavior and Ecology
- Medical Image Segmentation Techniques
- Neurobiology of Language and Bilingualism
- Smart Agriculture and AI
- Visual Attention and Saliency Detection
- Neural and Behavioral Psychology Studies
- Species Distribution and Climate Change
- Remote Sensing in Agriculture
- Insect Pest Control Strategies
- Neural Networks and Applications
- Child and Animal Learning Development
KU Leuven
2017-2023
Recent studies showed agreement between how the human brain and neural networks represent objects, suggesting that we might start to understand underlying computations. However, know is prone biases at many perceptual cognitive levels, often shaped by learning history evolutionary constraints. Here, explore one such phenomenon, perceiving animacy, use performance of as a benchmark. We performed an fMRI study dissociated object appearance (what looks like) from category (animate or inanimate)...
Sticky trap catches of agricultural pests can be employed for early hotspot detection, identification, and estimation pest presence in greenhouses or the field. However, manual procedures to produce analyze catch results require substantial time effort. As a result, much research has gone into creating efficient techniques remotely monitoring possible infestations. A considerable number these studies use Artificial Intelligence (AI) acquired data focus on performance metrics various model...
Abstract Functional MRI studies in primates have demonstrated cortical regions that are strongly activated by visual images of bodies. The presence such body patches macaques allows characterization the stimulus selectivity their single neurons. Middle superior temporal sulcus (MSB) patch neurons showed similar for natural, shaded, and textured compared with silhouettes, suggesting shape is an important determinant MSB responses. Here, we examined modeled We measured responses to a variety...
Recent studies suggest that deep Convolutional Neural Network (CNN) models show higher representational similarity, compared to any other existing object recognition models, with macaque inferior temporal (IT) cortical responses, human ventral stream fMRI activations and recognition. These employed natural images of objects. A long research tradition abstract shapes probe the selectivity IT neurons. If CNN provide a realistic model then they should capture for such shapes. Here, we compare...
The spotted wing Drosophila (SWD), suzukii, is a significant invasive pest of berries and soft-skinned fruits that causes major economic losses in fruit production worldwide. Automatic identification monitoring strategies would allow to detect the emergence this an early stage minimize its impact. small size suzukii similar flying insects makes it difficult identify them using camera systems. Therefore, optical sensor recording wingbeats was investigated study. We trained convolutional...
KEY POINTSThis article draws attention to key developments in the field of computer vision for industrial quality control and provides some illustrative examples.
According to a recent study, semantic similarity between concrete entities correlates with the of activity patterns in left middle IPS during category naming. We examined replicability this effect under passive viewing conditions, potential role visuoperceptual similarity, where is situated compared regions that have been previously implicated visuospatial attention, and how it compares effects object identity location. Forty-six subjects participated. Subjects passively viewed pictures from...
Abstract Recent studies showed agreement between how the human brain and neural networks represent objects, suggesting that we might start to understand underlying computations. However, know is prone biases at many perceptual cognitive levels, often shaped by learning history evolutionary constraints. Here explore one such bias, namely bias perceive animacy, used performance of as a benchmark. We performed an fMRI study dissociated object appearance (how looks like) from category (animate...
The ventral visual pathway contains rich representations of objects, with information about both their properties and category membership at multiple hierarchical levels, including animate versus inanimate. These neural show general agreement behavioral similarity judgments representational similarities in "deep" convolutional networks. In this event-related functional neuroimaging study (n = 16), we challenge state-of-the-art by dissociating object appearance (how does the look like?) from...
We modelled the shape selectivity of single neurons midSTS body patch macaques (Popivanov et al., J. Neurosci., 2014). employed "adaptive stimulus sampling" (Brincat and Connor, Nat. 2004), producing shapes that were adapted on-line to response each neuron during recordings. This procedure resulted in a large number shapes, eliciting wide range responses for neuron. fit quantitative models separately (n = 77). cross-validation fitting procedures model's performance was evaluated with data...