people

research

Out-of-Distribution Learning

Out-of-Distribution learning is concerned with developing methods where the distribution of the data processed at test time may be different from the distrib...

Immersive Analytics

Recent advanecs in augmented, mixed, and virtual reality, coupled with the need to perform analysis and decision-making on large-scale collections of volumet...

Biomedical and Health Data Analysis

The effort to improve healthcare delivery by making medicine more personalized, precise and efficient, presents many challenges that require the acquisition,...

Novelty and Anomaly Detection

Detecting the presence of outliers, like novelties or anomalies, with respect to a particular distribution has numerous applications in computer vision and i...

Face Recognition

Human identification based on facial traits has made remarkable progress thanks to deep learning-based methods, but there are still challenges, for example r...

Plant Image Analysis

Modern precision agriculture takes advantage of image data collected from various platforms to monitor crops and optimize their management and maximize yield.

Person Re-Identification

Long-duration tracking of individuals across large sites is a challenge. Trucks of individuals from disjoint fields of view need to be linked, despite the sa...

Activity Recognition

Providing a semantic interpretation of the actions and interactions between the actors in a scene enables behavior analysis for automated decision-making. Th...

Object Detection

Object detection consists in automatically localizing and recognizing in images the presence of objects belonging to a predefined set of categories, and it i...

Video Tracking

Video tracking is the process of localizing an object in video at every time instant. It is a challenging problem especially when there are multiple objects ...

Dynamic Textures

One of the most important elements of modern Computer Vision is the concept of image texture, or simply texture. Depending on the task at hand (e.g. image-ba...

3D Object Modeling

Building 3D models is an important problem in several areas, such as forensic applications, medical applications, industrial inspection, or virtual visits of...

resources

DARMA Dataset

Repository of the Detection as A Reinforced Means of Attention fine-grained dataset.

ALAE Code

Code repository of the Adversarial Latent Autoencoder architecture.

GPND Code

Code repository of the Generalized Prbabilistic Novelty Detection model.

SDSH Code

Code repository of the Spherical Deep Supervised Hashing model.

CCSA Code

Code repository of the Classification and Contrastive Semantic Alignment domain adaptation model.

HAUS Dataset

Repository of the Human Activities Under Surveillance video dataset.