Bus Violence: An Open Benchmark for Video Violence Detection on Public Transport.

The automatic detection of violent actions in public places through video analysis is difficult because the employed Artificial Intelligence-based techniques often suffer from generalization problems. Indeed, these algorithms hinge on large quantities of annotated data and usually experience a drastic drop in performance when used in scenarios never seen during the supervised learning phase. In this paper, we introduce and publicly release the Bus Violence benchmark, the first large-scale collection of video clips for violence detection on public transport, where some actors simulated violent actions inside a moving bus in changing conditions, such as the background or light. Moreover, we conduct a performance analysis of several state-of-the-art video violence detectors pre-trained with general violence detection databases on this newly established use case. The achieved moderate performances reveal the difficulties in generalizing from these popular methods, indicating the need to have this new collection of labeled data, beneficial for specializing them in this new scenario.

An embedded toolset for human activity monitoring in critical environments.

In many working and recreational activities, there are scenarios where both individual and collective safety have to be constantly checked and properly signaled, as occurring in dangerous workplaces or during pandemic events like the recent COVID-19 disease. From wearing personal protective equipment to filling physical spaces with an adequate number of people, it is clear that a possibly automatic solution would help to check compliance with the established rules. Based on an off-the-shelf compact and low-cost hardware, we present a deployed real use-case embedded system capable of perceiving people's behavior and aggregations and supervising the appliance of a set of rules relying on a configurable plug-in framework. Working on indoor and outdoor environments, we show that our implementation of counting people aggregations, measuring their reciprocal physical distances, and checking the proper usage of protective equipment is an effective yet open framework for monitoring human activities in critical conditions.

Virtual to Real Adaptation of Pedestrian Detectors.

Pedestrian detection through Computer Vision is a building block for a multitude of applications. Recently, there has been an increasing interest in convolutional neural network-based architectures to execute such a task. One of these supervised networks' critical goals is to generalize the knowledge learned during the training phase to new scenarios with different characteristics. A suitably labeled dataset is essential to achieve this purpose. The main problem is that manually annotating a dataset usually requires a lot of human effort, and it is costly. To this end, we introduce ViPeD (Virtual Pedestrian Dataset), a new synthetically generated set of images collected with the highly photo-realistic graphical engine of the video game GTA V (Grand Theft Auto V), where annotations are automatically acquired. However, when training solely on the synthetic dataset, the model experiences a Synthetic2Real domain shift leading to a performance drop when applied to real-world images. To mitigate this gap, we propose two different domain adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection. Experiments show that the network trained with ViPeD can generalize over unseen real-world scenarios better than the detector trained over real-world data, exploiting the variety of our synthetic dataset. Furthermore, we demonstrate that with our domain adaptation techniques, we can reduce the Synthetic2Real domain shift, making the two domains closer and obtaining a performance improvement when testing the network over the real-world images.

A comprehensive atlas of perineuronal net distribution and colocalization with parvalbumin in the adult mouse brain.

Perineuronal nets (PNNs) surround specific neurons in the brain and are involved in various forms of plasticity and clinical conditions. However, our understanding of the PNN role in these phenomena is limited by the lack of highly quantitative maps of PNN distribution and association with specific cell types. Here, we present a comprehensive atlas of Wisteria floribunda agglutinin (WFA)-positive PNNs and colocalization with parvalbumin (PV) cells for over 600 regions of the adult mouse brain. Data analysis shows that PV expression is a good predictor of PNN aggregation. In the cortex, PNNs are dramatically enriched in layer 4 of all primary sensory areas in correlation with thalamocortical input density, and their distribution mirrors intracortical connectivity patterns. Gene expression analysis identifies many PNN-correlated genes. Strikingly, PNN-anticorrelated transcripts are enriched in synaptic plasticity genes, generalizing PNNs' role as circuit stability factors.

Chemical Composition and Antimicrobial Activity against the Listeria monocytogenes of Essential Oils from Seven Salvia Species.

In recent years, essential oils (EOs) have received interest due to their antibacterial properties. Accordingly, the present study aimed to investigate the effectiveness of the EOs obtained from seven species of Salvia on three strains of Listeria monocytogenes (two serotyped wild strains and one ATCC strain), a bacterium able to contaminate food products and cause foodborne disease in humans. The Salvia species analysed in the present study were cultivated at the Botanic Garden and Museum of the University of Pisa, and their air-dried aerial parts were subjected to hydrodistillation using a Clevenger apparatus. The obtained EOs were analysed via gas chromatography coupled with mass spectrometry for the evaluation of their chemical composition, and they were tested for their inhibitory and bactericidal activities by means of MIC and MBC. The tested Eos showed promising results, and the best outcomes were reached by S. chamaedryoides EO, showing an MIC of 1:256 and an MBC of 1:64. The predominant compounds of this EO were the sesquiterpenes caryophyllene oxide and ß-caryophyllene, together with the monoterpenes bornyl acetate and borneol. These results suggest that these EOs may possibly be used in the food industry as preservatives of natural origins.

Learning to count biological structures with raters' uncertainty.

Exploiting well-labeled training sets has led deep learning models to astonishing results for counting biological structures in microscopy images. However, dealing with weak multi-rater annotations, i.e., when multiple human raters disagree due to non-trivial patterns, remains a relatively unexplored problem. More reliable labels can be obtained by aggregating and averaging the decisions given by several raters to the same data. Still, the scale of the counting task and the limited budget for labeling prohibit this. As a result, making the most with small quantities of multi-rater data is crucial. To this end, we propose a two-stage counting strategy in a weakly labeled data scenario. First, we detect and count the biological structures; then, in the second step, we refine the predictions, increasing the correlation between the scores assigned to the samples and the raters' agreement on the annotations. We assess our methodology on a novel dataset comprising fluorescence microscopy images of mice brains containing extracellular matrix aggregates named perineuronal nets. We demonstrate that we significantly enhance counting performance, improving confidence calibration by taking advantage of the redundant information characterizing the small sets of available multi-rater data.

Bridging the gap between high school and University studies for student with disability.

The choice of the university program represents an important and difficult step for a large part of high school students, especially for those who have to change city and lifestyle to follow their ambitions. In particular, for students with disabilities this choice is even more complicated due to their specific needs concerning both their educational and everyday life. In order to bridge the gap between high school and the University of Pisa, supporting the students during the selection of the program and their stay in Pisa, this paper presents a new model for matching the needs of the students and the existing services in Pisa, with particular attention to those with disabilities. It is based on questionnaires to assess the needs of the students and an accessible website to make available information about places and services offered in Pisa and its surrounding.