Abstract: In somatic cells, chromosomes occupy specific nuclear regions called chromosome territories which are involved in the
maintenance and regulation of the genome. Preliminary data in male germ cells also suggest the importance of chromosome
territoriality in cell functionality. Nevertheless, the specific characteristics of testicular tissue (presence of different
cell types with different morphological characteristics, in different stages of development and with different ploidy)
makes difficult to achieve conclusive results. In this study we have developed a methodology to approach the threedimensional
study of all chromosome territories in male germ cells from C57BL/6J mice (Mus musculus). The method
includes the following steps: i) Optimized cell fixation to obtain an optimal preservation of the three-dimensionality cell
morphology, ii) Chromosome identification by FISH (Chromoprobe Multiprobe® OctoChrome™ Murine System; Cytocell)
and confocal microscopy (TCS-SP5, Leica Microsystems), iii) Cell type identification by immunofluorescence
iv) Image analysis using Matlab scripts, v) Numerical data extraction related to chromosome features, chromosome
radial position and chromosome relative position. This methodology allows the unequivocally identification and the
analysis of the chromosome territories of all spermatogenic stages. Results will provide information about the features
that determine chromosomal position, preferred associations between chromosomes, and the relationship between chromosome
positioning and genome regulation.

Abstract: Bag of visual words (BoVW) models are widely utilized in image/ video representation and recognition. The cornerstone of these models is the encoding stage, in which local features are decomposed over a codebook in order to obtain a representation of features. In this paper, we propose a new encoding algorithm by jointly encoding the set of local descriptors of each sample and considering the locality structure of descriptors. The proposed method takes advantages of locality coding such as its stability and robustness to noise in descriptors, as well as the strengths of the group coding strategy by taking into account the potential relation among descriptors of a sample. To efficiently implement our proposed method, we consider the Alternating Direction Method of Multipliers (ADMM) framework, which results in quadratic complexity in the problem size. The method is employed for a challenging classification problem: action recognition by depth cameras. Experimental results demonstrate the outperformance of our methodology compared to the state-of-the-art on the considered datasets.

Abstract: Recognizing human actions in videos is a challenging problem in computer vision. Recently, convolutional neural network based deep features have shown promising results for action recognition. In this paper, we investigate the problem of fusing deep appearance and motion cues for action recognition. We propose a video representation which combines deep appearance and motion based local convolutional features within the bag-of-deep-features framework. Firstly, dense deep appearance and motion based local convolutional features are extracted from spatial (RGB) and temporal (flow) networks, respectively. Both visual cues are processed in parallel by constructing separate visual vocabularies for appearance and motion. A category-specific appearance map is then learned to modulate the weights of the deep motion features. The proposed representation is discriminative and binds the deep local convolutional features to their spatial locations. Experiments are performed on two challenging datasets: JHMDB dataset with 21 action classes and ACT dataset with 43 categories. The results clearly demonstrate that our approach outperforms both standard approaches of early and late feature fusion. Further, our approach is only employing action labels and without exploiting body part information, but achieves competitive performance compared to the state-of-the-art deep features based approaches.

Abstract: Eye tracker devices have traditionally been only used inside laboratories, requiring trained professionals and elaborate setup mechanisms. However, in the recent years the scientific work on easier–to–use eye trackers which require no special hardware—other than the omnipresent front facing cameras in computers, tablets, and mobiles—is aiming at making this technology common–place. These types of trackers have several extra challenges that make the problem harder, such as low resolution images provided by a regular webcam, the changing ambient lighting conditions, personal appearance differences, changes in head pose, and so on. Recent research in the field has focused on all these challenges in order to provide better gaze estimation performances in a real world setup.
In this work, we aim at tackling the gaze tracking problem in a single camera setup. We first analyze all the previous work in the field, identifying the strengths and weaknesses of each tried idea. We start our work on the gaze tracker with an appearance–based gaze estimation method, which is the simplest idea that creates a direct mapping between a rectangular image patch extracted around the eye in a camera image, and the gaze point (or gaze direction). Here, we do an extensive analysis of the factors that affect the performance of this tracker in several experimental setups, in order to address these problems in future works. In the second part of our work, we propose a feature–based gaze estimation method, which encodes the eye region image into a compact representation. We argue that this type of representation is better suited to dealing with head pose and lighting condition changes, as it both reduces the dimensionality of the input (i.e. eye image) and breaks the direct connection between image pixel intensities and the gaze estimation. Lastly, we use a face alignment algorithm to have robust face pose estimation, using a 3D model customized to the subject using the tracker. We combine this with a convolutional neural network trained on a large dataset of images to build a face pose invariant gaze tracker.

Abstract: This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly explored two multimodal architectures where either global visual features or convolutional feature maps are integrated in order to benefit from visual context. Our final systems ranked first for both En-De and En-Fr language pairs according to the automatic evaluation metrics METEOR and BLEU.

Abstract: This paper focuses on near infrared (NIR) image colorization by using a Conditional Deep Convolutional Generative Adversarial Network (CDCGAN) architecture model. The proposed architecture is based on the usage of a conditional probabilistic generative model. Firstly, it learns to colorize the given input image, by using a triplet model architecture that tackle every channel in an independent way. In the proposed model, the nal layer of red channel consider the infrared image to enhance the details, resulting in a sharp RGB image. Then, in the second stage, a discriminative model is used to estimate the probability that the generated image came from the training dataset, rather than the image automatically generated. Experimental results with a large set of real images are provided showing the validity of the proposed approach. Additionally, the proposed approach is compared with a state of the art approach showing better results.