Abstract: Food plays an important role in several aspects of our daily life. Several computer vision approaches have been proposed for tackling food analysis problems, but very little effort has been done in developing methodologies that could take profit of the existent correlation between tasks. In this paper, we propose a new multi-task model that is able to simultaneously predict different food-related tasks, e.g. dish, cuisine and food categories. Here, we extend the homoscedastic uncertainty modeling to allow single-label and multi-label classification and propose a regularization term, which jointly weighs the tasks as well as their correlations. Furthermore, we propose a new Multi-Attribute Food dataset and a new metric, Multi-Task Accuracy. We prove that using both our uncertainty-based loss and the class regularization term, we are able to improve the coherence of outputs between different tasks. Moreover, we outperform the use of task-specific models on classical measures like accuracy or .

Abstract: The human visual system is able to recognize the object in an image even if the object is partially occluded, from various points of view, in different colors, or with independence of the distance to the object. To do this, the eye obtains an image and extracts features that are sent to the brain, and then, in the brain the object is recognized. In computer vision, the object recognition branch tries to learns from the human visual system behaviour to achieve its goal. Hence, an algorithm is used to identify representative features of the scene (detection), then another algorithm is used to describe these points (descriptor) and finally the extracted information is used for classifying the object in the scene. The selection of this set of algorithms is a very complicated task and thus, a very active research field. In this thesis we are focused on the selection/learning of the best descriptor for a given image. In the state of the art there are several descriptors but we do not know how to choose the best descriptor because depends on scenes that we will use (dataset) and the algorithm chosen to do the classification. We propose a framework based on reinforcement learning and bag of features to choose the best descriptor according to the given image. The system can analyse the behaviour of different learning algorithms and descriptor sets. Furthermore the proposed framework for improving the classification/recognition ratio can be used with minor changes in other computer vision fields, such as video retrieval.

Abstract: PMID 23231293
PURPOSE:
Atheromatic plaque progression is affected, among others phenomena, by biomechanical, biochemical, and physiological factors. In this paper, the authors introduce a novel framework able to provide both morphological (vessel radius, plaque thickness, and type) and biomechanical (wall shear stress and Von Mises stress) indices of coronary arteries.
METHODS:
First, the approach reconstructs the three-dimensional morphology of the vessel from intravascular ultrasound (IVUS) and Angiographic sequences, requiring minimal user interaction. Then, a computational pipeline allows to automatically assess fluid-dynamic and mechanical indices. Ten coronary arteries are analyzed illustrating the capabilities of the tool and confirming previous technical and clinical observations.
RESULTS:
The relations between the arterial indices obtained by IVUS measurement and simulations have been quantitatively analyzed along the whole surface of the artery, extending the analysis of the coronary arteries shown in previous state of the art studies. Additionally, for the first time in the literature, the framework allows the computation of the membrane stresses using a simplified mechanical model of the arterial wall.
CONCLUSIONS:
Circumferentially (within a given frame), statistical analysis shows an inverse relation between the wall shear stress and the plaque thickness. At the global level (comparing a frame within the entire vessel), it is observed that heavy plaque accumulations are in general calcified and are located in the areas of the vessel having high wall shear stress. Finally, in their experiments the inverse proportionality between fluid and structural stresses is observed.

Abstract: Graphical documents express complex concepts using a visual language. This language consists of a vocabulary (symbols) and a syntax (structural relations between symbols) that articulate a semantic meaning in a certain context. Therefore, the automatic interpretation by computers of these sort of documents entails three main steps: the detection of the symbols, the extraction of the structural relations between these symbols, and the modeling of the knowledge that permits the extraction of the semantics. Dierent domains in graphical documents include: architectural and engineering drawings, maps, owcharts, etc.
Graphics Recognition in particular and Document Image Analysis in general are
born from the industrial need of interpreting a massive amount of digitalized documents after the emergence of the scanner. Although many years have passed, the graphical document understanding problem still seems to be far from being solved. The main reason is that the vast majority of the systems in the literature focus on very specic problems, where the domain of the document dictates the implementation of the interpretation. As a result, it is dicult to reuse these strategies on dierent data and on dierent contexts, hindering thus the natural progress in the eld.
In this thesis, we face the graphical document understanding problem by proposing several relational models at dierent levels that are designed from a generic perspective. Firstly, we introduce three dierent strategies for the detection of symbols. The first method tackles the problem structurally, wherein general knowledge of the domain guides the detection. The second is a statistical method that learns the graphical appearance of the symbols and easily adapts to the big variability of the problem. The third method is a combination of the previous two methods that inherits their respective strengths, i.e. copes the big variability and does not need annotated data. Secondly, we present two relational strategies that tackle the problem of the visual context extraction. The first one is a full bottom up method that heuristically searches in a graph representation the contextual relations between symbols. Contrarily, the second is syntactic method that models probabilistically the structure of the documents. It automatically learns the model, which guides the inference algorithm to encounter the best structural representation for a given input. Finally, we construct a knowledge-based model consisting of an ontological denition of the domain and real data. This model permits to perform contextual reasoning and to detect semantic inconsistencies within the data. We evaluate the suitability of the proposed contributions in the framework of floor plan interpretation. Since there is no standard in the modeling of these documents there exists an enormous notation variability from plan to plan in terms of vocabulary and syntax. Therefore, floor plan interpretation is a relevant task in the graphical document understanding problem. It is also worth to mention that we make freely available all the resources used in this thesis {the data, the tool used to generate the data, and the evaluation scripts{ with the aim of fostering research in the graphical document understanding task.

Abstract: Video retrieval using natural language queries has attracted increasing interest due to its relevance in real-world applications, from intelligent access in private media galleries to web-scale video search. Learning the cross-similarity of video and text in a joint embedding space is the dominant approach. To do so, a contrastive loss is usually employed because it organizes the embedding space by putting similar items close and dissimilar items far. This framework leads to competitive recall rates, as they solely focus on the rank of the groundtruth items. Yet, assessing the quality of the ranking list is of utmost importance when considering intelligent retrieval systems, since multiple items may share similar semantics, hence a high relevance. Moreover, the aforementioned framework uses a fixed margin to separate similar and dissimilar items, treating all non-groundtruth items as equally irrelevant. In this paper we propose to use a variable margin: we argue that varying the margin used during training based on how much relevant an item is to a given query, i.e. a relevance-based margin, easily improves the quality of the ranking lists measured through nDCG and mAP. We demonstrate the advantages of our technique using different models on EPIC-Kitchens-100 and YouCook2. We show that even if we carefully tuned the fixed margin, our technique (which does not have the margin as a hyper-parameter) would still achieve better performance. Finally, extensive ablation studies and qualitative analysis support the robustness of our approach. Code will be released at \urlhttps://github.com/aranciokov/RelevanceMargin-ICMR22.

Abstract: In our work, we are particularly interested in studying the shadows cast by static objects in outdoor environments, during daytime. To assess the accuracy of a shadow detection algorithm, we need ground truth information. The collection of such information is a very tedious task because it is a process that requires manual annotation. To overcome this severe limitation, we propose in this paper a methodology to automatically render ground truth using a virtual environment. To increase the degree of realism and usefulness of the simulated environment, we incorporate in the scenario the precise longitude, latitude and elevation of the actual location of the object, as well as the sun’s position for a given time and day. To evaluate our method, we consider a qualitative and a quantitative comparison. In the quantitative one, we analyze the shadow cast by a real object in a particular geographical location and its corresponding rendered model. To evaluate qualitatively the methodology, we use some ground truth images obtained both manually and automatically.