Open University of Catalonia

About: Open University of Catalonia is a education organization based out in Barcelona, Spain. It is known for research contribution in the topics: Context (language use) & Higher education. The organization has 1943 authors who have published 4646 publications receiving 64200 citations. The organization is also known as: Universitat Oberta de Catalunya & UOC.

Context Based Emotion Recognition Using EMOTIC Dataset

Abstract: In our everyday lives and social interactions we often try to perceive the emotional states of people. There has been a lot of research in providing machines with a similar capacity of recognizing emotions. From a computer vision perspective, most of the previous efforts have been focusing in analyzing the facial expressions and, in some cases, also the body pose. Some of these methods work remarkably well in specific settings. However, their performance is limited in natural, unconstrained environments. Psychological studies show that the scene context, in addition to facial expression and body pose, provides important information to our perception of people's emotions. However, the processing of the context for automatic emotion recognition has not been explored in depth, partly due to the lack of proper data. In this paper we present EMOTIC, a dataset of images of people in a diverse set of natural situations, annotated with their apparent emotion. The EMOTIC dataset combines two different types of emotion representation: (1) a set of 26 discrete categories, and (2) the continuous dimensions Valence , Arousal , and Dominance . We also present a detailed statistical and algorithmic analysis of the dataset along with annotators’ agreement analysis. Using the EMOTIC dataset we train different CNN models for emotion recognition, combining the information of the bounding box containing the person with the contextual information extracted from the scene. Our results show how scene context provides important information to automatically recognize emotional states and motivate further research in this direction.

Digital Photography and Picture Sharing: Redefining the Public/Private Divide

Abstract: Digital photography is contributing to the renegotiation of the public and private divide and to the transformation of privacy and intimacy, especially with the convergence of digital cameras, mobile phones, and web sites. This convergence contributes to the redefinition of public and private and to the transformation of their boundaries, which have always been subject to historical and geographical change. Taking pictures or filming videos of strangers in public places and showing them in webs like Flickr or YouTube, or making self-portraits available to strangers in instant messenger, social network sites, or photo blogs are becoming a current practice for a growing number of Internet users. Both are examples of the intertwining of online and offline practices, experiences, and meanings that challenge the traditional concepts of the public and the private. Uses of digital images play a role in the way people perform being a stranger and in the way they relate to strangers, online and offline. The mere claims about the privatization of the public space or the public disclosure of intimacy do not account for all these practices, situations, and attitudes, as they are not a simple translation of behaviors and codes from one realm to the other.

Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data.

Abstract: Multiple sclerosis (MS) can be divided into four phenotypes based on clinical evolution. The pathophysiological boundaries of these phenotypes are unclear, limiting treatment stratification. Machine learning can identify groups with similar features using multidimensional data. Here, to classify MS subtypes based on pathological features, we apply unsupervised machine learning to brain MRI scans acquired in previously published studies. We use a training dataset from 6322 MS patients to define MRI-based subtypes and an independent cohort of 3068 patients for validation. Based on the earliest abnormalities, we define MS subtypes as cortex-led, normal-appearing white matter-led, and lesion-led. People with the lesion-led subtype have the highest risk of confirmed disability progression (CDP) and the highest relapse rate. People with the lesion-led MS subtype show positive treatment response in selected clinical trials. Our findings suggest that MRI-based subtypes predict MS disability progression and response to treatment and may be used to define groups of patients in interventional trials.

Empirical validation of the Gamification User Types Hexad scale in English and Spanish

Abstract: Gamification, the use of game elements in non-game systems, is now established as a relevant research field in human-computer interaction (HCI). Several empirical studies have shown that gameful interventions can increase engagement and generate desired behavioral outcomes in HCI applications. However, some inconclusive results indicate that we need a fuller understanding of the mechanisms and effects of gamification. The Gamification User Types Hexad scale allows us to parse different user motivations in participants’ interactions with gameful applications, which are measured using a self-report questionnaire. Each user type represents a style of interaction with gameful applications, for example, if the interactions are more focused on achievements, socialization, or rewards. Thus, by scoring an individual in each one of the user types of the Hexad model, we can establish a profile of user preferences for gameful interactions. However, we still lack a substantial empirical validation of this scale. Therefore, we set out to validate the factor structure of the scale, in both English and Spanish, by conducting three studies, which also investigated the distribution of the Hexad's user types in the sample. Our findings support the structural validity of the scale, as well as suggesting opportunities for improvement. Furthermore, we demonstrate that some user types are more common than others and that gender and age correlate with a person's user types. Our work contributes to HCI research by further validating the utility of the Gamification User Types Hexad scale, potentially affording researchers a deeper understanding of the mechanisms and effects of gameful interventions.