Abstract: Video alignment is important in different areas of computer vision such as wide baseline matching, action recognition, change detection, video copy detection and frame dropping prevention. Current video alignment methods usually deal with a relatively simple case of fixed or rigidly attached cameras or simultaneous acquisition. Therefore, in this paper we propose a joint video alignment for bringing two video sequences into a spatio-temporal alignment. Specifically, the novelty of the paper is to formulate the video alignment to fold the spatial and temporal alignment into a single alignment framework. This simultaneously satisfies a frame-correspondence and frame-alignment similarity; exploiting the knowledge among neighbor frames by a standard pairwise Markov random field (MRF). This new formulation is able to handle the alignment of sequences recorded at different times by independent moving cameras that follows a similar trajectory, and also generalizes the particular cases that of fixed geometric transformation and/or linear temporal mapping. We conduct experiments on different scenarios such as sequences recorded simultaneously or by moving cameras to validate the robustness of the proposed approach. The proposed method provides the highest video alignment accuracy compared to the state-of-the-art methods on sequences recorded from vehicles driving along the same track at different times.

Abstract: Food photos are widely used in food logs for diet monitoring and in social networks to share social and gastronomic experiences. A large number of these images are taken in restaurants. Dish recognition in general is very challenging, due to different cuisines, cooking styles, and the intrinsic difficulty of modeling food from its visual appearance. However, contextual knowledge can be crucial to improve recognition in such scenario. In particular, geocontext has been widely exploited for outdoor landmark recognition. Similarly, we exploit knowledge about menus and location of restaurants and test images. We first adapt a framework based on discarding unlikely categories located far from the test image. Then, we reformulate the problem using a probabilistic model connecting dishes, restaurants, and locations. We apply that model in three different tasks: dish recognition, restaurant recognition, and location refinement. Experiments on six datasets show that by integrating multiple evidences (visual, location, and external knowledge) our system can boost the performance in all tasks.

Abstract: Fine-grained image recognition is central to many multimedia tasks such as search, retrieval, and captioning. Unfortunately, these tasks are still challenging since the appearance of samples of the same class can be more different than those from different classes. This issue is mainly due to changes in deformation, pose, and the presence of clutter. In the literature, attention has been one of the most successful strategies to handle the aforementioned problems. Attention has been typically implemented in neural networks by selecting the most informative regions of the image that improve classification. In contrast, in this paper, attention is not applied at the image level but to the convolutional feature activations. In essence, with our approach, the neural model learns to attend to lower-level feature activations without requiring part annotations and uses those activations to update and rectify the output likelihood distribution. The proposed mechanism is modular, architecture-independent, and efficient in terms of both parameters and computation required. Experiments demonstrate that well-known networks such as wide residual networks and ResNeXt, when augmented with our approach, systematically improve their classification accuracy and become more robust to changes in deformation and pose and to the presence of clutter. As a result, our proposal reaches state-of-the-art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford Dogs, and UEC-Food100 while obtaining competitive performance in ImageNet, CIFAR-100, CUB200 Birds, and Stanford Cars. In addition, we analyze the different components of our model, showing that the proposed attention modules succeed in finding the most discriminative regions of the image. Finally, as a proof of concept, we demonstrate that with only local predictions, an augmented neural network can successfully classify an image before reaching any fully connected layer, thus reducing the computational amount up to 10%.

Abstract: Intestinal motility assessment with video capsule endoscopy arises as a novel and challenging clinical fieldwork. This technique is based on the analysis of the patterns of intestinal contractions shown in a video provided by an ingestible capsule with a wireless micro-camera. The manual labeling of all the motility events requires large amount of time for offline screening in search of findings with low prevalence, which turns this procedure currently unpractical. In this paper, we propose a machine learning system to automatically detect the phasic intestinal contractions in video capsule endoscopy, driving a useful but not feasible clinical routine into a feasible clinical procedure. Our proposal is based on a sequential design which involves the analysis of textural, color, and blob features together with SVM classifiers. Our approach tackles the reduction of the imbalance rate of data and allows the inclusion of domain knowledge as new stages in the cascade. We present a detailed analysis, both in a quantitative and a qualitative way, by providing several measures of performance and the assessment study of interobserver variability. Our system performs at 70% of sensitivity for individual detection, whilst obtaining equivalent patterns to those of the experts for density of contractions.

Abstract: Vessel plaque assessment by analysis of intravascular ultrasound sequences is a useful tool for cardiac disease diagnosis and intervention. Manual detection of luminal (inner) and mediaadventitia (external) vessel borders is the main activity of physicians in the process of lumen narrowing (plaque) quantification. Difficult definition of vessel border descriptors, as well as, shades, artifacts, and blurred signal response due to ultrasound physical properties trouble automated adventitia segmentation. In order to efficiently approach such a complex problem, we propose blending advanced anisotropic filtering operators and statistical classification techniques into a vessel border modelling strategy. Our systematic statistical analysis shows that the reported adventitia detection achieves an accuracy in the range of interobserver variability regardless of plaque nature, vessel geometry, and incomplete vessel borders. Index Terms–-Anisotropic processing, intravascular ultrasound (IVUS), vessel border segmentation, vessel structure classification.

Abstract: Tissue biomechanical properties (like strain and stress) are playing an increasing role in diagnosis and long-term treatment of intravascular coronary diseases. Their assessment strongly relies on estimation of vessel wall deformation. Since intravascular ultrasound (IVUS) sequences allow visualizing vessel morphology and reflect its dynamics, this technique represents a useful tool for evaluation of tissue mechanical properties. Image misalignment introduced by vessel-catheter motion is a major artifact for a proper tracking of tissue deformation. In this work, we focus on compensating and assessing IVUS rigid in-plane motion due to heart beating. Motion parameters are computed by considering both the vessel geometry and its appearance in the image. Continuum mechanics laws serve to introduce a novel score measuring motion reduction in in vivo sequences. Synthetic experiments validate the proposed score as measure of motion parameters accuracy; whereas results in in vivo pullbacks show the reliability of the presented methodologies in clinical cases.

Abstract: The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.