Publications

La presente invenzione descrive un metodo e sistema per il riconoscimento biometrico univoco di un animale, basato sull’utilizzo di tecniche di deep learning. Il metodo è caratterizzato dalle seguenti fasi: a. fase di allenamento su di un dominio umano ed un dominio animale per l’ottenimento di embedding animali in uno spazio latente omologo a quello umano per mezzo di reti neurali convolutive; b. memorizzazione degli embedding animali ottenuti in una banca dati; c. riconoscimento di una identità animale per mezzo di reti neurali convolutive. La presente invenzione comprende anche un sistema per il riconoscimento biometrico univoco di un animale che utilizza il metodo precedentemente descritto.

People re-identification task has seen enormous improvements in the latest years, mainly due to the development of better image features extraction from deep Convolutional Neural Networks (CNN) and the availability of large datasets. However, little research has been conducted on animal identification and re-identification, even if this knowledge may be useful in a rich variety of different scenarios. Here, we tackle cattle re-identification exploiting deep CNN and show how this task is poorly related to the human one, presenting unique challenges that make it far from being solved. We present various baselines, both based on deep architectures or on standard machine learning algorithms, and compared them with our solution. Finally, a rich ablation study has been conducted to further investigate the unique peculiarities of this task.

Connected Components Labeling (CCL) is a fundamental image processing technique, widely used in various application areas. Computational throughput of Graphical Processing Units (GPUs) makes them eligible for such a kind of algorithms. In the last decade, many approaches to compute CCL on GPUs have been proposed. Unfortunately, most of them have focused on 4-way connectivity neglecting the importance of 8-way connectivity. This paper aims to extend state-of-the-art GPU-based algorithms from 4 to 8-way connectivity and to improve them with additional optimizations. Experimental results revealed the effectiveness of the proposed strategies.

Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural Networks to generate the corresponding captions. At the same time, a significant research effort has been dedicated to the development of saliency prediction models, which can predict human eye fixations. Despite saliency information could be useful to condition an image captioning architecture, by providing an indication of what is salient and what is not, no model has yet succeeded in effectively incorporating these two techniques. In this work, we propose an image captioning approach in which a generative recurrent neural network can focus on different parts of the input image during the generation of the caption, by exploiting the conditioning given by a saliency prediction model on which parts of the image are salient and which are contextual. We demonstrate, through extensive quantitative and qualitative experiments on large scale datasets, that our model achieves superior performances with respect to different image captioning baselines with and without saliency. Finally, we also show that the trained model can focus on salient and contextual regions during the generation of the caption in an appropriate way.

Understanding human gaze behaviour in social context, as along a face-to-face interaction, remains an open research issue which is strictly related to personality traits. In the effort to bridge the gap between available data and models, typical approaches focus on the analysis of spatial and temporal preferences of gaze deployment over specific regions of the observed face, while adopting classic statistical methods. In this note we propose a different analysis perspective based on novel data-mining techniques and a probabilistic classification method that relies on Gaussian Processes exploiting Automatic Relevance Determination (ARD) kernel. Preliminary results obtained on a publicly available dataset are provided.

Most of the crowd abnormal event detection methods rely on complex hand-crafted features to represent the crowd motion and appearance. Convolutional Neural Networks (CNN) have shown to be a powerful instrument with excellent representational capacities, which can leverage the need for hand-crafted features. In this paper, we show that keeping track of the changes in the CNN feature across time can be used to effectively detect local anomalies. Specifically, we propose to measure local abnormality by combining semantic information (inherited from existing CNN models) with low-level optical-flow. One of the advantages of this method is that it can be used without the fine-tuning phase. The proposed method is validated on challenging abnormality detection datasets and the results show the superiority of our approach compared with the state-of-the art methods.

Data-driven saliency has recently gained a lot of attention thanks to the use of Convolutional Neural Networks for predicting gaze fixations. In this paper we go beyond standard approaches to saliency prediction, in which gaze maps are computed with a feed-forward network, and present a novel model which can predict accurate saliency maps by incorporating neural attentive mechanisms. The core of our solution is a Convolutional LSTM that focuses on the most salient regions of the input image to iteratively refine the predicted saliency map. Additionally, to tackle the center bias typical of human eye fixations, our model can learn a set of prior maps generated with Gaussian functions. We show, through an extensive evaluation, that the proposed architecture outperforms the current state of the art on public saliency prediction datasets. We further study the contribution of each key component to demonstrate their robustness on different scenarios.

The SACHER project provides a distributed, open source and federated cloud platform able to support the life-cycle management of various kinds of data concerning tangible Cultural Heritage. The paper describes the SACHER platform and, in particular, among the various integrated service prototypes, the most important ones to support restoration processes and cultural asset management: (i) 3D Life Cycle Management for Cultural Heritage (SACHER 3D CH), based on 3D digital models of architecture and dedicated to the management of Cultural Heritage and to the storage of the numerous data generated by the team of professionals involved in the restoration process; (ii) Multidimensional Search Engine for Cultural Heritage (SACHER MuSE CH), an advanced multi-level search system designed to manage Heritage data from heterogeneous sources.

The prediction of human eye fixations has been recently gaining a lot of attention thanks to the improvements shown by deep architectures. In our work, we go beyond classical feed-forward networks to predict saliency maps and propose a Saliency Attentive Model which incorporates neural attention mechanisms to iteratively refine predictions. Experiments demonstrate that the proposed strategy overcomes by a considerable margin the state of the art on the largest dataset available for saliency prediction. Here, we provide experimental results on other popular saliency datasets to confirm the effectiveness and the generalization capabilities of our model, which enable us to reach the state of the art on all considered datasets.