Search

The Social and hUman ceNtered XR (SUN) project is focused on developing eXtended Reality (XR) solutions that integrate the physical and virtual world in a way that is convincing from a human and social perspective. In this paper, we outline the limitations that the SUN project aims to overcome, including the lack of scalable and cost-effective solutions for developing XR applications, limited solutions for mixing the virtual and physical environment, and barriers related to resource limitations of end-user devices. We also propose solutions to these limitations, including using artificial intelligence, computer vision, and sensor analysis to incrementally learn the visual and physical properties of real objects and generate convincing digital twins in the virtual environment. Additionally, the SUN project aims to provide wearable sensors and haptic interfaces to enhance natural interaction with the virtual environment and advanced solutions for user interaction. Finally, we describe three real-life scenarios in which we aim to demonstrate the proposed solutions.

Multimedia data manipulation and forgery has never been easier than today, thanks to the power of Artificial Intelligence (AI). AI-generated fake content, commonly called Deepfakes, have been raising new issues and concerns, but also new challenges for the research community. The Deepfake detection task has become widely addressed, but unfortunately, approaches in the literature suffer from generalization issues. In this paper, the Face Deepfake Detection and Reconstruction Challenge is described. Two different tasks were proposed to the participants: (i) creating a Deepfake detector capable of working in an “in the wild” scenario; (ii) creating a method capable of reconstructing original images from Deepfakes. Real images from CelebA and FFHQ and Deepfake images created by StarGAN, StarGAN-v2, StyleGAN, StyleGAN2, AttGAN and GDWCT were collected for the competition. The winning teams were chosen with respect to the highest classification accuracy value (Task I) and “minimum average distance to Manhattan” (Task II). Deep Learning algorithms, particularly those based on the EfficientNet architecture, achieved the best results in Task I. No winners were proclaimed for Task II. A detailed discussion of teams’ proposed methods with corresponding ranking is presented in this paper.

Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks. Current computer vision techniques rely on deep learning-based algorithms that estimate pedestrian densities in still, individual images. Only a bunch of works take advantage of temporal consistency in video sequences. In this work, we propose a spatio-temporal attentive neural network to estimate the number of pedestrians from surveillance videos. By taking advantage of the temporal correlation between consecutive frames, we lowered state-of-the-art count error by 5% and localization error by 7.5% on the widely-used FDST benchmark., Accepted at IEEE ISCC 2022

Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer vision, in this paper, we introduce the Recurrent Vision Transformer (RViT) model. Thanks to the impact of recurrent connections and spatial attention in reasoning tasks, this network achieves competitive results on the same-different visual reasoning problems from the SVRT dataset. The weight-sharing both in spatial and depth dimensions regularizes the model, allowing it to learn using far fewer free parameters, using only 28k training samples. A comprehensive ablation study confirms the importance of a hybrid CNN + Transformer architecture and the role of the feedback connections, which iteratively refine the internal representation until a stable prediction is obtained. In the end, this study can lay the basis for a deeper understanding of the role of attention and recurrent connections for solving visual abstract reasoning tasks.

This paper presents a communication framework built to simplify the construction of robotic ecologies, i.e., networks of heterogeneous computational nodes interfaced with sensors, actuators, and mobile robots. Building integrated ambient intelligence (AmI) solutions out of such a wide range of heterogeneous devices is a key requirement for a range of application domains, such as home automation, logistic, security and Ambient Assisted Living (AAL). This goal is challenging since these ecologies need to adapt to changing environments and especially when they include tiny embedded devices with limited computational resources. We discuss a number of requirements characterizing this type of systems and illustrate how they have been addressed in the design of the new communication framework. The most distinguishing aspect of our frameworks is the transparency with which the same communication features are offered across heterogeneous programming languages and operating systems under a consistent API. Finally, we illustrate how the framework has been used to bind together and to support the operations of all the components of adaptive robotic ecologies in two real-world test-beds.

Facial Expression Recognition(FER) is one of the most important topic in Human-Computer interactions(HCI). In this work we report details and experimental results about a facial expression recognition method based on state-of-the-art methods. We fine-tuned a SeNet deep learning architecture pre-trained on the well-known VGGFace2 dataset, on the AffWild2 facial expression recognition dataset. The main goal of this work is to define a baseline for a novel method we are going to propose in the near future. This paper is also required by the Affective Behavior Analysis in-the-wild (ABAW) competition in order to evaluate on the test set this approach. The results reported here are on the validation set and are related on the Expression Challenge part (seven basic emotion recognition) of the competition. We will update them as soon as the actual results on the test set will be published on the leaderboard.

Recent work has shown that biologically plausible Hebbian learning can be integrated with backpropagation learning (backprop), when training deep convolutional neural networks. In particular, it has been shown that Hebbian learning can be used for training the lower or the higher layers of a neural network. For instance, Hebbian learning is effective for re-training the higher layers of a pre-trained deep neural network, achieving comparable accuracy w.r.t. SGD, while requiring fewer training epochs, suggesting potential applications for transfer learning. In this paper we build on these results and we further improve Hebbian learning in these settings, by using a nonlinear Hebbian Principal Component Analysis (HPCA) learning rule, in place of the Hebbian Winner Takes All (HWTA) strategy used in previous work. We test this approach in the context of computer vision. In particular, the HPCA rule is used to train Convolutional Neural Networks in order to extract relevant features from the CIFAR-10 image dataset. The HPCA variant that we explore further improves the previous results, motivating further interest towards biologically plausible learning algorithms., 12 pages, 3 figures, 2 tables

The Artificial Intelligence for Media and Humanities laboratory (AIMH) has the mission to investigate and advance the state of the art in the Artificial Intelligence field, specifically addressing applications to digital media and digital humanities, and taking also into account issues related to scalability. This report summarize the 2020 activities of the research group.

Memory Based Collaborative Filtering is a widely used approach to provide recommendations. It exploits similarities between ratings across a population of users by forming a weighted vote to predict unobserved ratings. Bespoke solutions are frequently adopted to deal with the problem of high quality recommendations on large data sets. A disadvantage of this approach, however, is the loss of generality and flexibility of the general collaborative filtering systems. In this paper, we have developed a methodology that allows one to build a scalable and effective collaborative filtering system on top of a conventional full-text search engine such as Apache Lucene.

In this work, we propose an approach to index Deep Convolutional Neural Network Features to support efficient content-based retrieval on large image databases. To this aim, we have converted the these features into a textual form, to index them into an inverted index by means of Lucene. In this way, we were able to set up a robust retrieval system that combines full-text search with content-based image retrieval capabilities. We evaluated different strategies of textual representation in order to optimize the index occupation and the query response time. In order to show that our approach is able to handle large datasets, we have developed a web-based prototype that provides an interface for combined textual and visual searching into a dataset of about 100 million of images., This paper has been withdrawn by the author due to many errors

Similarity search for content-based retrieval (where content can be any combination of text, image, audio/video, etc.) has gained importance in recent years, also because of the advantage of ranking the retrieved results according to their proximity to a query. However, to use similarity search in real world applications, we need to tackle the problem of huge volumes of such mixed multimedia data (e.g., coming from Web sites) and the problem of their distribution on multiple cooperating nodes. The proposed approach is being used in two running projects: SAPIR and NeP4B. In this paper we approach this problem by considering a scenario of a network of autonomous peers maintaining a local collection of metric objects (i.e., mixed mode multimedia content). This network forms a distributed Peer--to--Peer (P2P) search engine for similarity search based on the paradigm of Routing Index. Each peer in the network thus maintains both an index of its local resources and a table for every neighbor, summarizing the objects that are reachable from it. The paper presents techniques that aim to make our P2P similarity-based search system viable, trading approximate results for scalable solutions. Results of simulations that use real collections of images are discussed.