Abstract: Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.

Abstract: Assessing the physical condition in rehabilitation scenarios is a challenging problem, since it involves Human Activity Recognition (HAR) and kinematic analysis methods. In addition, the difficulties increase in unconstrained rehabilitation scenarios, which are much closer to the real use cases. In particular, our aim is to design an upper-limb assessment pipeline for stroke patients using smartwatches. We focus on the HAR task, as it is the first part of the assessing pipeline. Our main target is to automatically detect and recognize four key movements inspired by the Fugl-Meyer assessment scale, which are performed in both constrained and unconstrained scenarios. In addition to the application protocol and dataset, we propose two detection and classification baseline methods. We believe that the proposed framework, dataset and baseline results will serve to foster this research field.

Abstract: People suffering Bipolar Disorder (BD) experiment changes in mood status having depressive or manic episodes with normal periods in the middle. BD is a chronic disease with a high level of non-adherence to medication that needs a continuous monitoring of patients to detect when they relapse in an episode, so that physicians can take care of them. Here we present MoodRecord, an easy-to-use, non-intrusive, multilingual, robust and scalable platform suitable for home monitoring patients with BD, that allows physicians and relatives to track the patient state and get alarms when abnormalities occur.
MoodRecord takes advantage of the capabilities of smartphones as a communication and recording device to do a continuous monitoring of patients. It automatically records user activity, and asks the user to answer some questions or to record himself in video, according to a predefined plan designed by physicians. The video is analysed, recognising the mood status from images and bipolar assessment scores are extracted from speech parameters. The data obtained from the different sources are merged periodically to observe if a relapse may start and if so, raise the corresponding alarm. The application got a positive evaluation in a pilot with users from three different countries. During the pilot, the predictions of the voice and image modules showed a coherent correlation with the diagnosis performed by clinicians.

Abstract: The automatic discovery of behaviour is of high importance when aiming to assess and improve the quality of life of people. Egocentric images offer a rich and objective description of the daily life of the camera wearer. This work proposes a new method to identify a person’s patterns of behaviour from collected egocentric photo-streams. Our model characterizes time-frames based on the context (place, activities and environment objects) that define the images composition. Based on the similarity among the time-frames that describe the collected days for a user, we propose a new unsupervised greedy method to discover the behavioural pattern set based on a novel semantic clustering approach. Moreover, we present a new score metric to evaluate the performance of the proposed algorithm. We validate our method on 104 days and more than 100k images extracted from 7 users. Results show that behavioural patterns can be discovered to characterize the routine of individuals and consequently their lifestyle.

Abstract: The recognition of food image is an interesting research topic, in which its applicability in the creation of nutritional diaries stands out with the aim of improving the quality of life of people with a chronic disease (e.g. diabetes, heart disease) or prone to acquire it (e.g. people with overweight or obese). For a food recognition system to be useful in real applications, it is necessary to recognize a huge number of different foods. We argue that for very large scale classification, a traditional flat classifier is not enough to acquire an acceptable result. To address this, we propose a method that performs prediction with local classifiers, based on a class hierarchy, or with flat classifier. We decide which approach to use, depending on the analysis of both the Epistemic Uncertainty obtained for the image in the children classifiers and the prediction of the parent classifier. When our criterion is met, the final prediction is obtained with the respective local classifier; otherwise, with the flat classifier. From the results, we can see that the proposed method improves the classification performance compared to the use of a single flat classifier.

Abstract: State of the art machine learning methods need huge amounts of data with unambiguous annotations for their training. In the context of medical imaging this is, in general, a very difficult task due to limited access to clinical data, the time required for manual annotations and variability across experts. Simulated data could serve for data augmentation provided that its appearance was comparable to the actual appearance of intra-operative acquisitions. Generative Adversarial Networks (GANs) are a powerful tool for artistic style transfer, but lack a criteria for selecting epochs ensuring also preservation of intra-operative content.
We propose a multi-objective optimization strategy for a selection of cycleGAN epochs ensuring a mapping between virtual images and the intra-operative domain preserving anatomical content. Our approach has been applied to simulate intra-operative bronchoscopic videos and chest CT scans from virtual sketches generated using simple graphical primitives.

Abstract: The routine of a person is defined by the occurrence of activities throughout different days, and can directly affect the person’s health. In this work, we address the recognition of routine related days. To do so, we rely on egocentric images, which are recorded by a wearable camera and allow to monitor the life of the user from a first-person view perspective. We propose an unsupervised model that identifies routine related days, following an outlier detection approach. We test the proposed framework over a total of 72 days in the form of photo-streams covering around 2 weeks of the life of 5 different camera wearers. Our model achieves an average of 76% Accuracy and 68% Weighted F-Score for all the users. Thus, we show that our framework is able to recognise routine related days and opens the door to the understanding of the behaviour of people.