Publications

In this chapter we address the problem of partitioning social gatherings into interacting groups in egocentric scenarios. People in the scene are tracked, their head pose and 3D location are estimated. Following the formalism of the f-formation, we define with the orientation and distance an inherently social pairwise feature capable of describing how two people stand in relation to one another. We present a Structural SVM based approach to learn how to weight each component of the feature vector depending on the social situation is applied to. To better understand the social dynamics, we also estimate what we call social relevance of each subject in a group using a saliency attentive model. Extensive tests on two publicly available datasets show that our solution achieves encouraging results when detecting social groups and their relevant subjects in the challenging egocentric scenarios.

This paper presents the results of the Eurographics 2019 SHape Retrieval Contest track on online gesture recognition. The goal of this contest was to test state-of-the-art methods that can be used to online detect command gestures from hands' movements tracking on a basic benchmark where simple gestures are performed interleaving them with other actions. Unlike previous contests and benchmarks on trajectory-based gesture recognition, we proposed an online gesture recognition task, not providing pre-segmented gestures, but asking the participants to find gestures within recorded trajectories. The results submitted by the participants show that an online detection and recognition of sets of very simple gestures from 3D trajectories captured with a cheap sensor can be effectively performed. The best methods proposed could be, therefore, directly exploited to design effective gesture-based interfaces to be used in different contexts, from Virtual and Mixed reality applications to the remote control of home devices.

The brain comprises a complex system of neurons interconnected by an intricate network of anatomical links. While recent studies demonstrated the correlation between anatomical connectivity patterns and gene expression of neurons, using transcriptomic information to automatically predict such patterns is still an open challenge. In this work, we present a completely data-driven approach relying on machine learning (i.e., neural networks) to learn the anatomical connection directly from a training set of gene expression data. To do so, we combined gene expression and connectivity data from the Allen Mouse Brain Atlas to generate thousands of gene expression profile pairs from different brain regions. To each pair, we assigned a label describing the physical connection between the corresponding brain regions. Then, we exploited these data to train neural networks, designed to predict brain area connectivity. We assessed our solution on two prediction problems (with three and two connectivity class categories) involving cortical and cerebellum regions. As demonstrated by our results, we distinguish between connected and unconnected regions with 85% prediction accuracy and good balance of precision and recall. In our future work we may extend the analysis to more complex brain structures and consider RNA-Seq data as additional input to our model.

We discuss a preliminary investigation on the feasibility of inferring traits of social participation from the observable behaviour of individuals involved in dyadic interactions. Trait inference relies on a stochastic model of the dynamics occurring in the individual core affect state-space. Results obtained on a publicly available interaction dataset are presented and examined.

In this paper, we introduce a novel GPU-based Connected Components Labeling algorithm: the Block-based Union Find. The proposed strategy significantly improves an existing GPU algorithm, taking advantage of a block-based approach. Experimental results on real cases and synthetically generated datasets demonstrate the superiority of the new proposal with respect to state-of-the-art.

Cross-modal retrieval has been recently becoming an hot-spot research, thanks to the development of deeply-learnable architectures. Such architectures generally learn a joint multi-modal embedding space in which text and images could be projected and compared. Here we investigate a different approach, and reformulate the problem of cross-modal retrieval as that of learning a translation between the textual and visual domain. In particular, we propose an end-to-end trainable model which can translate text into image features and vice versa, and regularizes this mapping with a cycle-consistency criterion. Preliminary experimental evaluations show promising results with respect to ordinary visual-semantic models.

Nowadays, single-cell DNA (sc-DNA) sequencing is showing up to be a valuable instrument to investigate intra and inter-tumor heterogeneity and infer its evolutionary dynamics, by using the high-resolution data it produces. That is why the demand for analytical tools to manage this kind of data is increasing. Here we propose a pipeline capable of producing multi-sample copy-number variation (CNV) analysis on large-scale single-cell DNA sequencing data and investigate spatial and temporal tumor heterogeneity.

Face recognition using a single reference image per subject is challenging, above all when referring to a large gallery of subjects. Furthermore, the problem hardness seriously increases when the images are acquired in unconstrained conditions. In this paper we address the challenging Single Sample Per Person (SSPP) problem considering large datasets of images acquired in the wild, thus possibly featuring illumination, pose, face expression, partial occlusions, and low-resolution hurdles. The proposed technique alternates a sparse dictionary learning technique based on the method of optimal direction and the iterative ℓ 0 -norm minimization algorithm called k-LIMAPS. It works on robust deep-learned features, provided that the image variability is extended by standard augmentation techniques. Experiments show the effectiveness of our method against the hardness introduced above: first, we report extensive experiments on the unconstrained LFW dataset when referring to large galleries up to 1680 subjects; second, we present experiments on very low-resolution test images up to 8 × 8 pixels; third, tests on the AR dataset are analyzed against specific disguises such as partial occlusions, facial expressions, and illumination problems. In all the three scenarios our method outperforms the state-of-the-art approaches adopting similar configurations.