Pedestrians and drivers are expected to safely navigate complex urban environments along with several non cooperating agents. Autonomous vehicles will soon replicate this capability. Each agent acquires a representation of the world from an egocentric perspective and must make decisions ensuring safety for itself and others. This requires to predict motion patterns of observed agents for a far enough future. In this paper we propose MANTRA, a model that exploits memory augmented networks to effectively predict multiple trajectories of other agents, observed from an egocentric perspective. Our model stores observations in memory and uses trained controllers to write meaningful pattern encodings and read trajectories that are most likely to occur in future. We show that our method is able to natively perform multi-modal trajectory prediction obtaining state-of-the art results on four datasets. Moreover, thanks to the non-parametric nature of the memory module, we show how once trained our system can continuously improve by ingesting novel patterns.

With the establishment of Industry 4.0 , machines are now required to interact with workers. By observing biometrics they can assess if humans are authorized, or mentally and physically fit to work. Understanding body language, makes human–machine interaction more natural, secure, and effective. Nonetheless, traditional cameras have limitations; low frame rate and dynamic range hinder a comprehensive human understanding. This poses a challenge, since faces undergo frequent instantaneous microexpressions. In addition, this is privacy-sensitive information that must be protected. We propose to model expressions with event cameras, bio-inspired vision sensors that have found application within the Industry 4.0 scope. They capture motion at millisecond rates and work under challenging conditions like low illumination and highly dynamic scenes. Such cameras are also privacy-preserving, making them extremely interesting for industry. We show that using event cameras, we can understand human reactions by only observing facial expressions. Comparison with red-green-blue (RGB)-based modeling demonstrates improved effectiveness and robustness.

Online stores have become fundamental for the fashion industry, revolving around recommendation systems to suggest appropriate items to customers. Such recommendations often suffer from a lack of diversity and propose items that are similar to previous purchases of a user. Recently, a novel kind of approach based on Memory Augmented Neural Networks (MANNs) has been proposed, aimed at recommending a variety of garments to create an outfit by complementing a given fashion item. In this article we address the task of compatible garment recommendation developing a MANN architecture by taking into account the co-occurrence of clothing attributes, such as shape and color, to compose an outfit. To this end we obtain disentangled representations of fashion items and store them in external memory modules, used to guide recommendations at inference time. We show that our disentangled representations are able to achieve significantly better performance compared to the state of the art and also provide interpretable latent spaces, giving a qualitative explanation of the recommendations.

Effective modeling of human interactions is of utmost importance when forecasting behaviors such as future trajectories. Each individual, with its motion, influences surrounding agents since everyone obeys to social non-written rules such as collision avoidance or group following. In this paper we model such interactions, which constantly evolve through time, by looking at the problem from an algorithmic point of view, i.e., as a data manipulation task. We present a neural network based on an end-to-end trainable working memory, which acts as an external storage where information about each agent can be continuously written, updated and recalled. We show that our method is capable of learning explainable cause-effect relationships between motions of different agents, obtaining state-of-the-art results on multiple trajectory forecasting datasets.

The capacity to create “fake” videos has recently raised concerns about the reliability of multimedia content. Identifying between true and false information is a critical step toward resolving this problem. On this issue, several algorithms utilizing deep learning and facial landmarks have yielded intriguing results. Facial landmarks are traits that are solely tied to the subject’s head posture. Based on this observation, we study how Head Pose Estimation (HPE) patterns may be utilized to detect deepfakes in this work. The HPE patterns studied are based on FSA-Net, SynergyNet, and WSM, which are among the most performant approaches on the state-of-the-art. Finally, using a machine learning technique based on K-Nearest Neighbor and Dynamic Time Warping, their temporal patterns are categorized as authentic or false. We also offer a set of experiments for examining the feasibility of using deep learning techniques on such patterns. The findings reveal that the ability to recognize a deepfake video utilizing an HPE pattern is dependent on the HPE methodology. On the contrary, performance is less dependent on the performance of the utilized HPE technique. Experiments are carried out on the FaceForensics++ dataset that presents both identity swap and expression swap examples. The findings show that FSA-Net is an effective feature extraction method for determining whether a pattern belongs to a deepfake or not. The approach is also robust in comparison to deepfake videos created using various methods or for different goals. In the mean the method obtain 86% of accuracy on the identity swap task and 86.5% of accuracy on the expression swap. These findings offer up various possibilities and future directions for solving the deepfake detection problem using specialized HPE approaches, which are also known to be fast and reliable.

Visual question answering has recently been settled as a fundamental multi-modal reasoning task of artificial intelligence that allows users to get information about visual content by asking questions in natural language. In the cultural heritage domain, this task can contribute to assisting visitors in museums and cultural sites, thus increasing engagement. However, the development of visual question answering models for cultural heritage is prevented by the lack of suitable large-scale datasets. To meet this demand, we built a large-scale heterogeneous and multilingual (Italian and English) dataset for cultural heritage that comprises approximately 500K Italian cultural assets and 6.5M question-answer pairs. We propose a novel formulation of the task that requires reasoning over both the visual content and an associated natural language description, and present baselines for this task. Results show that the current state of the art is reasonably effective but still far from satisfactory; therefore, further research in this area is recommended. Nonetheless, we also present a holistic baseline to address visual and contextual questions and foster future research on the topic.