Abstract: Machine learning experimentation under controlled scenarios and standard datasets is necessary to compare algorithms performance by evaluating all of them in the same setup. However, experimentation on how those algorithms perform on unconstrained data and applied tasks to solve real world problems is also a must to ascertain how that research can contribute to our society.
In this dissertation we experiment with the latest computer vision and natural language processing algorithms applying them to multimodal scene interpretation. Particularly, we research on how image and text understanding can be jointly exploited to address real world problems, focusing on learning from Social Media data.
We address several tasks that involve image and textual information, discuss their characteristics and offer our experimentation conclusions. First, we work on detection of scene text in images. Then, we work with Social Media posts, exploiting the captions associated to images as supervision to learn visual features, which we apply to multimodal semantic image retrieval. Subsequently, we work with geolocated Social Media images with associated tags, experimenting on how to use the tags as supervision, on location sensitive image retrieval and on exploiting location information for image tagging. Finally, we work on a specific classification problem of Social Media publications consisting on an image and a text: Multimodal hate speech classification.

Abstract: The EMPATHIC project develops and validates new interaction paradigms for personalized virtual coaches (VC) to promote healthy and independent aging. To this end, the work presented in this paper is aimed to analyze the interaction between the EMPATHIC-VC and the users. One of the goals of the project is to ensure an end-user driven design, involving senior users from the beginning and during each phase of the project. Thus, the paper focuses on some sessions where the seniors carried out interactions with a Wizard of Oz driven, simulated system. A coaching strategy based on the GROW model was used throughout these sessions so as to guide interactions and engage the elderly with the goals of the project. In this interaction framework, both the human and the system behavior were analyzed. The way the wizard implements the GROW coaching strategy is a key aspect of the system behavior during the interaction. The language used by the virtual agent as well as his or her physical aspect are also important cues that were analyzed. Regarding the user behavior, the vocal communication provides information about the speaker’s emotional status, that is closely related to human behavior and which can be extracted from the speech and language analysis. In the same way, the analysis of the facial expression, gazes and gestures can provide information on the non verbal human communication even when the user is not talking. In addition, in order to engage senior users, their preferences and likes had to be considered. To this end, the effect of the VC on the users was gathered by means of direct questionnaires. These analyses have shown a positive and calm behavior of users when interacting with the simulated virtual coach as well as some difficulties of the system to develop the proposed coaching strategy.

Abstract: Pain is a vital sign of human health and its automatic detection can be of crucial importance in many different contexts, including medical scenarios. While most available computer vision techniques are based on RGB, in this paper, we investigate the effect of combining RGB, depth, and thermal
facial images for pain detection and pain intensity level recognition. For this purpose, we extract energies released by facial pixels using a spatiotemporal filter. Experiments on a group of 12 elderly people applying the multimodal approach show that the proposed method successfully detects pain and recognizes between three intensity levels in 82% of the analyzed frames improving more than 6% over RGB only analysis in similar conditions.

Abstract: Over the past few decades human-computer interaction has become more important in our daily lives and research has developed in many directions: memory research, depression detection, and behavioural deficiency detection, lie detection, (hidden) emotion recognition etc. Because of that, the number of generic emotion and face databases or those tailored to specific needs have grown immensely large. Thus, a comprehensive yet compact guide is needed to help researchers find the most suitable database and understand what types of databases already exist. In this paper, different elicitation methods are discussed and the databases are primarily organized into neat and informative tables based on the format.

Abstract: Color description is a challenging task because of large variations in RGB values which occur due to scene accidental events, such as shadows, shading, specularities, illuminant color changes, and changes in viewing geometry. Traditionally, this challenge has been addressed by capturing the variations in physics-based models, and deriving invariants for the undesired variations. The drawback of this approach is that sets of distinguishable colors in the original color space are mapped to the same value in the photometric invariant space. This results in a drop of discriminative power of the color description. In this paper we take an information theoretic approach to color description. We cluster color values together based on their discriminative power in a classification problem. The clustering has the explicit objective to minimize the drop of mutual information of the final representation. We show that such a color description automatically learns a certain degree of photometric invariance. We also show that a universal color representation, which is based on other data sets than the one at hand, can obtain competing performance. Experiments show that the proposed descriptor outperforms existing photometric invariants. Furthermore, we show that combined with shape description these color descriptors obtain excellent results on four challenging datasets, namely, PASCAL VOC 2007, Flowers-102, Stanford dogs-120 and Birds-200.