Abstract: Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments,
etc.) and edges characterize the relationships between these primitives. However, these non-vectorial graph data cannot be straightforwardly plugged into off-the-shelf machine learning algorithms without a preliminary step of – explicit/implicit –graph vectorization and embedding. This embedding process
should be resilient to intra-class graph variations while being highly discriminant. In this paper, we propose a novel high-order stochastic graphlet embedding (SGE) that maps graphs into vector spaces. Our main contribution includes a new stochastic search procedure that efficiently parses a given graph and extracts/samples unlimitedly high-order graphlets. We consider
these graphlets, with increasing orders, to model local primitives as well as their increasingly complex interactions. In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision. When
combined with maximum margin classifiers, these graphlet-based representations have positive impact on the performance of pattern comparison and recognition as corroborated through extensive experiments using standard benchmark databases.

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: 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: Colonoscopy is the gold standard for colon cancer screening though still some polyps are missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack
of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection subchallenge, conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org) at the international conference on Medical Image Computing and Computer Assisted
Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks (CNNs) are the state of the art. Nevertheless it is also demonstrated that combining different methodologies can lead to an improved overall performance.

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: Despite recovering a normal coronary flow after acute myocardial infarction, percutaneous coronary intervention does not guarantee a proper perfusion (irrigation) of the infarcted area. This damage in microcirculation integrity may detrimentally affect the patient survival. Visual assessment of the myocardium opacification in contrast angiography serves to define a subjective score of the microcirculation integrity myocardial blush analysis (MBA). Although MBA correlates with patient prognosis its visual assessment is a very difficult task that requires of a highly expertise training in order to achieve a good intraobserver and interobserver agreement. In this paper, we provide objective descriptors of the myocardium staining pattern by analyzing the spectrum of the image local statistics. The descriptors proposed discriminate among the different phenomena observed in the angiographic sequence and allow defining an objective score of the myocardial perfusion.

Abstract: Depth information is essential for on-board perception in autonomous driving and driver assistance. Monocular depth estimation (MDE) is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Usually, this GT is acquired at training time through a calibrated multi-modal suite of sensors. However, also using only a monocular system at training time is cheaper and more scalable. This is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. In this paper, we perform monocular depth estimation by virtual-world supervision (MonoDEVS) and real-world SfM self-supervision. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision and addressing the virtual-to-real domain gap. Our MonoDEVSNet outperforms previous MDE CNNs trained on monocular and even stereo sequences.

Abstract: In this paper, we investigate the problem of visual odometry for ground vehicles based on the simultaneous utilization of multispectral cameras. It encompasses a stereo rig composed of an optical (visible) and thermal sensors. The novelty resides in the localization of the cameras as a stereo setup rather
than two monocular cameras of different spectrums. To the best of our knowledge, this is the first time such task is attempted. Log-Gabor wavelets at different orientations and scales are used to extract interest points from both images. These are then described using a combination of frequency and spatial information within the local neighborhood. Matches between the pairs of multimodal images are computed using the cosine similarity function based
on the descriptors. Pyramidal Lucas–Kanade tracker is also introduced to tackle temporal feature matching within challenging sequences of the data sets. The vehicle egomotion is computed from the triangulated 3-D points corresponding to the matched features. A windowed version of bundle adjustment incorporating
Gauss–Newton optimization is utilized for motion estimation. An outlier removal scheme is also included within the framework to deal with outliers. Multispectral data sets were generated and used as test bed. They correspond to real outdoor scenarios captured using our multimodal setup. Finally, detailed results validating the proposed strategy are illustrated.