Publications

Video Surveillance started decades ago to remotely monitor specific areas and allow control from human inspectors. Later, Computer Vision gradually replaced human monitoring, firstly through motion alerts and now with Deep Learning techniques. From the beginning of this journey, people have worried about the risk of privacy violations. This article surveys the main steps of Computer Vision in Video Surveillance, from early approaches for people detection and tracking to action analysis and language description, outlining the most relevant directions on the topic to deal with privacy concerns. We show how the relationship between Video Surveillance and privacy is a biased paradox since surveillance provides increased safety but does not necessarily require the people identification. Through experiments on action recognition and natural language description, we showcase that the paradox of surveillance and privacy can be solved by Artificial Intelligence and that the respect of human rights is not an impossible chimera.

Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single round. We achieve this by modulating the network's components using memory matrices, enabling the network to demonstrate selective unlearning behavior for any class after training. By discovering weights that are specific to each class, our approach also recovers a representation of the classes which is explainable by design. We test the proposed framework on small- and medium-scale image classification datasets, with both convolution- and Transformer-based backbones, showcasing the potential for explainable solutions through unlearning.

In the last years, the research interest in visual navigation towards objects in indoor environments has grown significantly. This growth can be attributed to the recent availability of large navigation datasets in photo-realistic simulated environments, like Gibson and Matterport3D. However, the navigation tasks supported by these datasets are often restricted to the objects present in the environment at acquisition time. Also, they fail to account for the realistic scenario in which the target object is a user-specific instance that can be easily confused with similar objects and may be found in multiple locations within the environment. To address these limitations, we propose a new task denominated Personalized Instance-based Navigation (PIN), in which an embodied agent is tasked with locating and reaching a specific personal object by distinguishing it among multiple instances of the same category. The task is accompanied by PInNED, a dedicated new dataset composed of photo-realistic scenes augmented with additional 3D objects. In each episode, the target object is presented to the agent using two modalities: a set of visual reference images on a neutral background and manually annotated textual descriptions. Through comprehensive evaluations and analyses, we showcase the challenges of the PIN task as well as the performance and shortcomings of currently available methods designed for object-driven navigation, considering modular and end-to-end agents.

The rapidly evolving fields of e-commerce and metaverse continue to seek innovative approaches to enhance the consumer experience. At the same time, recent advancements in the development of diffusion models have enabled generative networks to create remarkably realistic images. In this context, image-based virtual try-on, which consists in generating a novel image of a target model wearing a given in-shop garment, has yet to capitalize on the potential of these powerful generative solutions. This work introduces LaDI-VTON, the first Latent Diffusion textual Inversion-enhanced model for the Virtual Try-ON task. The proposed architecture relies on a latent diffusion model extended with a novel additional autoencoder module that exploits learnable skip connections to enhance the generation process preserving the model's characteristics. To effectively maintain the texture and details of the in-shop garment, we propose a textual inversion component that can map the visual features of the garment to the CLIP token embedding space and thus generate a set of pseudo-word token embeddings capable of conditioning the generation process. Experimental results on Dress Code and VITON-HD datasets demonstrate that our approach outperforms the competitors by a consistent margin, achieving a significant milestone for the task.

In recent years, Human Pose Estimation has achieved impressive results on RGB images. The advent of deep learning architectures and large annotated datasets have contributed to these achievements. However, little has been done towards estimating the human pose using depth maps, and especially towards obtaining a precise 3D body joint localization. To fill this gap, this paper presents RefiNet, a depth-based 3D human pose refinement framework. Given a depth map and an initial coarse 2D human pose, RefiNet regresses a fine 3D pose. The framework is composed of three modules, based on different data representations, i.e. 2D depth patches, 3D human skeletons, and point clouds. An extensive experimental evaluation is carried out to investigate the impact of the model hyper-parameters and to compare RefiNet with off-the-shelf 2D methods and literature approaches. Results confirm the effectiveness of the proposed framework and its limited computational requirements.

Morphing Attack, i.e. the elusion of face verification systems through a facial morphing operation between a criminal and an accomplice, has recently emerged as a serious security threat. Despite the importance of this kind of attack, the development and comparison of Morphing Attack Detection (MAD) methods is still a challenging task, especially with deep learning approaches. Specifically, the lack of public datasets, the absence of common training and validation protocols, and the limited release of public source code hamper the reproducibility and objective comparison of new MAD systems. Usually, these aspects are mainly due to privacy concerns, that limit data transfers and storage, and to the recent introduction of the MAD task. Therefore, in this paper, we propose and publicly release Revelio, a modular framework for the reproducible development and evaluation of MAD systems. We include an overview of the modules, and describe the plugin system providing the possibility of extending native components with new functionalities. An extensive cross-datasets experimental evaluation is conducted to validate the framework and the performance of trained models on several publicly-released datasets, and to deeply analyze the main challenges in the MAD task based on single input images. We also propose a new metric, namely WAED, to summarize in a single value the error-based metrics commonly used in the MAD task, computed over different datasets, thus facilitating the comparative evaluation of different approaches. Finally, by exploiting Revelio, a new state-of-the-art MAD model (on SOTAMD single-image benchmark) is proposed and released.

Generating synthetic images of handwritten text in a writer-specific style is a challenging task, especially in the case of unseen styles and new words, and even more when these latter contain characters that are rarely encountered during training. While emulating a writer's style has been recently addressed by generative models, the generalization towards rare characters has been disregarded. In this work, we devise a Transformer-based model for Few-Shot styled handwritten text generation and focus on obtaining a robust and informative representation of both the text and the style. In particular, we propose a novel representation of the textual content as a sequence of dense vectors obtained from images of symbols written as standard GNU Unifont glyphs, which can be considered their visual archetypes. This strategy is more suitable for generating characters that, despite having been seen rarely during training, possibly share visual details with the frequently observed ones. As for the style, we obtain a robust representation of unseen writers' calligraphy by exploiting specific pre-training on a large synthetic dataset. Quantitative and qualitative results demonstrate the effectiveness of our proposal in generating words in unseen styles and with rare characters more faithfully than existing approaches relying on independent one-hot encodings of the characters.

Artificial-intelligence-based methods are regularly used in the biomedical sciences, mainly in the field of diagnostic imaging. Recently, convolutional neural networks have been trained to score pleurisy and pneumonia in slaughtered pigs. The aim of this study is to further evaluate the performance of a convolutional neural network when compared with the gold standard (i.e., scores provided by a skilled operator along the slaughter chain through visual inspection and palpation). In total, 441 lungs (180 healthy and 261 diseased) are included in this study. Each lung was scored according to traditional methods, which represent the gold standard (Madec’s and Christensen’s grids). Moreover, the same lungs were photographed and thereafter scored by a trained convolutional neural network. Overall, the results reveal that the convolutional neural network is very specific (95.55%) and quite sensitive (85.05%), showing a rather high correlation when compared with the scores provided by a skilled veterinarian (Spearman’s coefficient = 0.831, p < 0.01). In summary, this study suggests that convolutional neural networks could be effectively used at slaughterhouses and stimulates further investigation in this field of research.