Abstract: The main objective of the EMPATHIC project has been the design and development of a virtual coach to engage the healthy-senior user and to enhance well-being through awareness of personal status. The EMPATHIC approach addresses this objective through multimodal interactions supported by the GROW coaching model. The paper summarizes the main components of the EMPATHIC Virtual Coach (EMPATHIC-VC) and introduces a demonstration of the coaching sessions in selected scenarios.

Abstract: The majority of existing color naming methods focuses on the eleven basic color terms of the English language. However, in many applications, different sets of color names are used for the accurate description of objects. Labeling data to learn these domain-specific color names is an expensive and laborious task. Therefore, in this article we aim to learn color names from weakly labeled data. For this purpose, we add an attention branch to the color naming network. The attention branch is used to modulate the pixel-wise color naming predictions of the network. In experiments, we illustrate that the attention branch correctly identifies the relevant regions. Furthermore, we show that our method obtains state-of-the-art results for pixel-wise and image-wise classification on the EBAY dataset and is able to learn color names for various domains.

Abstract: The manual inspection of intravascular ultrasound (IVUS) images to detect clinically relevant patterns is a difficult and laborious task performed routinely by physicians. In this paper, we present a framework based on convolutional nets for the quick selection of IVUS frames containing arterial calcification, a pattern whose detection plays a vital role in the diagnosis of atherosclerosis. Preliminary experiments on a dataset acquired from eighty patients show that convolutional architectures improve detections of a shallow classifier in terms of 𝐹1-measure, precision and recall.

Abstract: The mass irruption of Deep Convolutional Neural Networks (CNNs) in computer vision since 2012 led to a dominance of the image understanding paradigm consisting in an end-to-end fully supervised learning workflow over large-scale annotated datasets. This approach proved to be extremely useful at solving a myriad of classic and new computer vision tasks with unprecedented performance —often, surpassing that of humans—, at the expense of vast amounts of human-labeled data, extensive computational resources and the disposal of all of our prior knowledge on the task at hand. Even though simple transfer learning methods, such as fine-tuning, have achieved remarkable impact, their success when the amount of labeled data in the target domain is small is limited. Furthermore, the non-static nature of data generation sources will often derive in data distribution shifts that degrade the performance of deployed models. As a consequence, there is a growing demand for methods that can exploit elements of prior knowledge and sources of information other than the manually generated ground truth annotations of the images during the network training process, so that they can adapt to new domains that constitute, if not a small data regime, at least a small labeled data regime. This thesis targets such few or no labeled data scenario in three distinct image-to-image mapping learning problems. It contributes with various approaches that leverage our previous knowledge of different elements of the image formation process: We first present a data-efficient framework for both defocus and motion blur detection, based on a model able to produce realistic synthetic local degradations. The framework comprises a self-supervised, a weakly-supervised and a semi-supervised instantiation, depending on the absence or availability and the nature of human annotations, and outperforms fully-supervised counterparts in a variety of settings. Our knowledge on color image formation is then used to gather input and target ground truth image pairs for the RGB to hyperspectral image reconstruction task. We make use of a CNN to tackle this problem, which, for the first time, allows us to exploit spatial context and achieve state-of-the-art results given a limited hyperspectral image set. In our last contribution to the subfield of data-efficient image-to-image transformation problems, we present the novel semi-supervised task of zero-pair cross-view semantic segmentation: we consider the case of relocation of the camera in an end-to-end trained and deployed monocular, fixed-view semantic segmentation system often found in industry. Under the assumption that we are allowed to obtain an additional set of synchronized but unlabeled image pairs of new scenes from both original and new camera poses, we present ZPCVNet, a model and training procedure that enables the production of dense semantic predictions in either source or target views at inference time. The lack of existing suitable public datasets to develop this approach led us to the creation of MVMO, a large-scale Multi-View, Multi-Object path-traced dataset with per-view semantic segmentation annotations. We expect MVMO to propel future research in the exciting under-developed fields of cross-view and multi-view semantic segmentation. Last, in a piece of applied research of direct application in the context of process monitoring of an Electric Arc Furnace (EAF) in a steelmaking plant, we also consider the problem of simultaneously estimating the temperature and spectral emissivity of distant hot emissive samples. To that end, we design our own capturing device, which integrates three point spectrometers covering a wide range of the Ultra-Violet, visible, and Infra-Red spectra and is capable of registering the radiance signal incoming from an 8cm diameter spot located up to 20m away. We then define a physically accurate radiative transfer model that comprises the effects of atmospheric absorbance, of the optical system transfer function, and of the sample temperature and spectral emissivity themselves. We solve this inverse problem without the need for annotated data using a probabilistic programming-based Bayesian approach, which yields full posterior distribution estimates of the involved variables that are consistent with laboratory-grade measurements.

Abstract: The median graph has been presented as a useful tool to represent a set of graphs. Nevertheless its computation is very complex and the existing algorithms are restricted to use limited amount of data. In this paper we propose a new approach for the computation of the median graph based on graph embedding. Graphs are embedded into a vector space and the median is computed in the vector domain. We have designed a procedure based on the weighted mean of a pair of graphs to go from the vector domain back to the graph domain in order to obtain a final approximation of the median graph. Experiments on three different databases containing large graphs show that we succeed to compute good approximations of the median graph. We have also applied the median graph to perform some basic classification tasks achieving reasonable good results. These experiments on real data open the door to the application of the median graph to a number of more complex machine learning algorithms where a representative of a set of graphs is needed.

Abstract: The median graph has been shown to be a good choice to obtain a represen- tative of a set of graphs. However, its computation is a complex problem. Recently, graph embedding into vector spaces has been proposed to obtain approximations of the median graph. The problem with such an approach is how to go from a point in the vector space back to a graph in the graph space. The main contribution of this paper is the generalization of this previ- ous method, proposing a generic recursive procedure that permits to recover the graph corresponding to a point in the vector space, introducing only the amount of approximation inherent to the use of graph matching algorithms. In order to evaluate the proposed method, we compare it with the set me- dian and with the other state-of-the-art embedding-based methods for the median graph computation. The experiments are carried out using four dif- ferent databases (one semi-artificial and three containing real-world data). Results show that with the proposed approach we can obtain better medi- ans, in terms of the sum of distances to the training graphs, than with the previous existing methods.

Abstract: The mixture of parts model has been successfully applied to solve the 2D
human pose estimation problem either as an explicitly trained body part model
or as latent variables for pedestrian detection. Even in the era of massive
applications of deep learning techniques, the mixture of parts model is still
effective in solving certain problems, especially in the case with limited
numbers of training samples. In this paper, we consider using the mixture of
parts model for pose estimation, wherein a tree structure is utilized for
representing relations between connected body parts. This strategy facilitates
training and inferencing of the model but suffers from double counting
problems, where one detected body part is counted twice due to lack of
constrains among unconnected body parts. To solve this problem, we propose a
generalized solution in which various part attributes are captured by multiple
features so as to avoid the double counted problem. Qualitative and
quantitative experimental results on a public available dataset demonstrate the
effectiveness of our proposed method.
An Effective Solution to Double Counting Problem in Human Pose Estimation – ResearchGate. Available from: http://www.researchgate.net/publication/271218491AnEffectiveSolutiontoDoubleCountingProbleminHumanPose_Estimation [accessed Oct 22, 2015].

Abstract: The most relevant modules of a pedestrian detector are the candidate generation and the candidate classification. The former aims at presenting image windows to the latter so that they are classified as containing a pedestrian or not. Much attention has being paid to the classification module, while candidate generation has mainly relied on (multiscale) sliding window pyramid. However, candidate generation is critical for achieving real-time. In this paper we assume a context of autonomous driving based on stereo vision. Accordingly, we evaluate the effect of taking into account the 3D information (derived from the stereo) in order to prune the hundred of thousands windows per image generated by classical pyramidal sliding window. For our study we use a multimodal (RGB, disparity) and multi-descriptor (HOG, LBP, HOG+LBP) holistic ensemble based on linear SVM. Evaluation on data from the challenging KITTI benchmark suite shows the effectiveness of using 3D information to dramatically reduce the number of candidate windows, even improving the overall pedestrian detection accuracy.