Sorry, you need to enable JavaScript to visit this website.

We propose a deep learning framework for few-shot image classification, which exploits information across label semantics and image domains, so that regions of interest can be properly attended for improved classification. The proposed semantics-guided attention module is able to focus on most relevant regions in an image, while the attended image samples allow data augmentation and alleviate possible overfitting during FSL training. Promising performances are presented in our experiments, in which we consider both closed and open-world settings.

In recent years, light fields have become a major research topic and their applications span across the entire spectrum of classical image processing. Among the different methods used to capture a light field are the lenslet cameras, such as those developed by Lytro. While these cameras give a lot of freedom to the user, they also create light field views that suffer from a number of artefacts. As a result, it is common to ignore a significant subset of these views when doing high-level light field processing.

Point cloud are precise digital record of an objects in space. It starts to getting more attention due to the additional information it provides compared to 2D images. In this paper, we propose a new deep learning architecture called R-CovNets, designed for 3D object recognition. Unlike to previous approaches that usually sample or convert point cloud into three-dimensional grids, R-CovNets does not reckon on any preprocessing. Our architecture is specially designed for cloud point, permutation invariant and can take as input, a data of any size.

Time-lapse microscopy provides 4D imaging data for monitoring and studying down to single-cell, the stochastic processes involved as bacterial colonies grow and interact under different stress conditions. Two main factors prevent high throughput analysis: a) cell segmentation and tracking are very time-consuming and error-prone and b) analytics tools are lacking to interpret the plethora of features extracted from a complex “cell-movie.” To address both limitations, we have recently developed a multi-resolution Bio-image Analysis & Single-Cell Analytics framework, called BaSCA.

This paper presents the software architecture of a robotic museum guide application called CUMA.
It is intended to run upon the Pepper robotic platform and has the objective of guiding visitors of a museum accompanying them in the tour, explaining museum works, and interacting with them in order to gather feedback.

Fine-grained recognition focuses on the challenging task of automatically identifying the subtle differences between similar categories. Current state-of-the-art approaches require elaborated feature learning procedures, involving tuning several hyper-parameters, or rely on expensive human annotations such as objects or parts location. In this paper we propose a simple method for fine-grained recognition that exploits a nearly cost-free attention-based focus operation to construct an ensemble of increasingly specialized Convolutional Neural Networks.