Abstract: This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. We explored various comparative methods, namely phrase-based systems and attentional recurrent neural networks models trained using monomodal or multimodal data. We also performed a human evaluation in order to estimate theusefulness of multimodal data for human machine translation and image description generation. Our systems obtained the best results for both tasks according to the automatic evaluation metrics BLEU and METEOR.

Abstract: Natural and intuitive human interaction with robotic systems is a key point to develop robots assisting people in an easy and effective way. In this paper, a Human Robot Interaction (HRI) system able to recognize gestures usually employed in human non-verbal communication is introduced, and an in-depth study of its usability is performed. The system deals with dynamic gestures such as waving or nodding which are recognized using a Dynamic Time Warping approach based on gesture specific features computed from depth maps. A static gesture consisting in pointing at an object is also recognized. The pointed location is then estimated in order to detect candidate objects the user may refer to. When the pointed object is unclear for the robot, a disambiguation procedure by means of either a verbal or gestural dialogue is performed. This skill would lead to the robot picking an object in behalf of the user, which could present difficulties to do it by itself. The overall system — which is composed by a NAO and Wifibot robots, a KinectTM v2 sensor and two laptops — is firstly evaluated in a structured lab setup. Then, a broad set of user tests has been completed, which allows to assess correct performance in terms of recognition rates, easiness of use and response times.

Abstract: In real-life logistics and distribution activities it is usual to face situations in which the distribution of goods has to be made from multiple warehouses or depots to the nal customers. This problem is known as the Multi-Depot Vehicle Routing Problem (MDVRP), and it typically includes two sequential and correlated stages: (a) the assignment map of customers to depots, and (b) the corresponding design of the distribution routes. Most of the existing work in the literature has focused on minimizing distance-based distribution costs while satisfying a number of capacity constraints. However, no attention has been given so far to potential variations in demands due to the tness of the customerdepot mapping in the case of heterogeneous depots. In this paper, we consider this realistic version of the problem in which the depots are heterogeneous in terms of their commercial oer and customers show dierent willingness to consume depending on how well the assigned depot ts their preferences. Thus, we assume that dierent customer-depot assignment maps will lead to dierent customer-expenditure levels. As a consequence, market-segmentation strategiesneed to be considered in order to increase sales and total income while accounting for the distribution costs. To solve this extension of the MDVRP, we propose a hybrid approach that combines statistical learning techniques with a metaheuristic framework. First, a set of predictive models is generated from historical data. These statistical models allow estimating the demand of any customer depending on the assigned depot. Then, the estimated expenditure of each customer is included as part of an enriched objective function as a way to better guide the stochastic local search inside the metaheuristic framework. A set of computational experiments contribute to illustrate our approach and how the extended MDVRP considered here diers in terms of the proposed solutions from the traditional one.

Abstract: Facial expressions are an important way through which humans interact socially. Building a system capable of automatically recognizing facial expressions from images and video has been an intense field of study in recent years. Interpreting such expressions remains challenging and much research is needed about the way they relate to human affect. This paper presents a general overview of automatic RGB, 3D, thermal and multimodal facial expression analysis. We define a new taxonomy for the field, encompassing all steps from face detection to facial expression recognition, and describe and classify the state of the art methods accordingly. We also present the important datasets and the bench-marking of most influential methods. We conclude with a general discussion about trends, important questions and future lines of research.

Abstract: Latest advances in digitization techniques have fostered the interest in creating digital copies of collections of documents. Digitized documents permit an easy maintenance, loss-less storage, and efficient ways for transmission and to perform information retrieval processes. This situation has opened a new market niche to develop systems able to automatically extract and analyze information contained in these collections, specially in the ambit of the business activity.
Due to the great variety of types of documents this is not a trivial task. For instance, the automatic extraction of numerical data from invoices differs substantially from a task of text recognition in historical documents. However, in order to extract the information of interest, is always necessary to identify the area of the document where it is located. In the area of Document Analysis we refer to this process as layout analysis, which aims at identifying and categorizing the different entities that compose the document, such as text regions, pictures, text lines, or tables, among others. To perform this task it is usually necessary to incorporate a prior knowledge about the task into the analysis process, which can be modeled by defining a set of contextual relations between the different entities of the document. The use of context has proven to be useful to reinforce the recognition process and improve the results on many computer vision tasks. It presents two fundamental questions: What kind of contextual information is appropriate for a given task, and how to incorporate this information into the models.
In this thesis we study several ways to incorporate contextual information to the task of document layout analysis, and to the particular case of handwritten text line segmentation. We focus on the study of Probabilistic Graphical Models and other mechanisms for this purpose, and propose several solutions to these problems. First, we present a method for layout analysis based on Conditional Random Fields. With this model we encode local contextual relations between variables, such as pair-wise constraints. Besides, we encode a set of structural relations between different classes of regions at feature level. Second, we present a method based on 2D-Probabilistic Context-free Grammars to encode structural and hierarchical relations. We perform a comparative study between Probabilistic Graphical Models and this syntactic approach. Third, we propose a method for structured documents based on Bayesian Networks to represent the document structure, and an algorithm based in the Expectation-Maximization to find the best configuration of the page. We perform a thorough evaluation of the proposed methods on two particular collections of documents: a historical collection composed of ancient structured documents, and a collection of contemporary documents. In addition, we present a general method for the task of handwritten text line segmentation. We define a probabilistic framework where we combine the EM algorithm with variational approaches for computing inference and parameter learning on a Markov Random Field. We evaluate our method on several collections of documents, including a general dataset of annotated administrative documents. Results demonstrate the applicability of our method to real problems, and the contribution of the use of contextual information to this kind of problems.

Abstract: We present a computational model that computes and integrates in a nonlocal fashion several configural cues for automatic figure-ground segregation. Our working hypothesis is that the figural status of each pixel is a nonlocal function of several geometric shape properties and it can be estimated without explicitly relying on object boundaries. The methodology is grounded on two elements: multi-directional linear voting and nonlinear diffusion. A first estimation of the figural status of each pixel is obtained as a result of a voting process, in which several differently oriented line-shaped neighborhoods vote to express their belief about the figural status of the pixel. A nonlinear diffusion process is then applied to enforce the coherence of figural status estimates among perceptually homogeneous regions. Computer simulations fit human perception and match the experimental evidence that several cues cooperate in defining figure-ground segregation. The results of this work suggest that figure-ground segregation involves feedback from cells with larger receptive fields in higher visual cortical areas.