Domestic violence has increased globally as the COVID-19 pandemic combines with economic and social stresses. Some works have used traditional feature extractors to identify body positions to detect physical violence. Besides, the use of Machine Learning is limited by the trade-off between collecting more data while keeping users' privacy. Federated Learning (FL) is a technique that allows the creation of client-server networks, in which anonymized training data can be uploaded to a central model, responsible for aggregating and keeping the model up to date, and then distributing the updated model to the clients' nodes. This paper proposed an FL approach to the violence detection problem in video. The framework was evaluated on AIRTLab Dataset, in which frames were extracted. It used pretrained Convolutional Neural Networks (CNN) to address the image classification problem. Inception v3, MobileNet v2, ResNet-152 v2, and VGG-16 architectures were evaluated, with the MobileNet architecture presenting the best performance, in terms of accuracy (99.4%), with a loss of 0.5% when compared to the non-FL setting.

No abstract available.

Personalized algorithms focusing uniquely on accuracy might provide highly relevant recommendations, but the recommended items could be too similar to current users' preferences. Therefore, recommenders might prevent users from exploring new products and brands (filter bubbles). This is especially critical for luxury fashion recommendations because luxury shoppers expect to discover exclusive and rare items. Thus, recommender systems for fashion need to consider diversity and elevate the shopping experience by recommending new brands and products from the catalog. In this work, we explored a handful of diversification strategies to rerank the output of a relevance-focused recommender system. Subsequently, we conducted a multi-objective offline experiment optimizing for relevance and diversity simultaneously. We measured diversity with commonly used metrics such as coverage, serendipity, and neighborhood distance, whereas, for relevance, we selected ranking metrics such as recall. The best diversification strategy offline improved user engagement by 2% in click-through rate and presented an uplift of 46% in distinct brands recommended when AB tested against real users. These results reinforced the importance of considering accuracy and diversity metrics when developing a recommender system.