Abstract: In this paper, we propose a new data-driven approach for binary descriptor selection. In order to draw a clear analysis of common designs, we present a general information-theoretic selection paradigm. It encompasses several standard binary descriptor construction schemes, including a recent state-of-the-art one named BOLD. We pursue the same endeavor to increase the stability of the produced descriptors with respect to rotations. To achieve this goal, we have designed a novel offline selection criterion which is better adapted to the online matching procedure. The effectiveness of our approach is demonstrated on two standard datasets, where our descriptor is compared to BOLD and to several classical descriptors. In particular, it emerges that our approach can reproduce equivalent if not better performance as BOLD while relying on twice shorter descriptors. Such an improvement can be influential for real-time applications.

Abstract: We explore the potential of the use of blood vessels as anatomical landmarks for developing image registration methods in colonoscopy images. An unequivocal representation of blood vessels could be used to guide follow-up methods to track lesions over different interventions. We propose a graph-based representation to characterize network structures, such as blood vessels, based on the use of intersections and endpoints. We present a study consisting of the assessment of the minimal performance a keypoint detector should achieve so that the structure can still be recognized. Experimental results prove that, even by achieving a loss of 35% of the keypoints, the descriptive power of the associated graphs to the vessel pattern is still high enough to recognize blood vessels.

Abstract: During the last decades, the performance of optical music recognition has been increasingly improving. However, and despite the 2-dimensional nature of music notation (e.g. notes have rhythm and pitch), most works treat musical scores as a sequence of symbols in one dimension, which make their recognition still a challenge. Thus, in this work we explore the use of graph neural networks for musical score recognition. First, because graphs are suited for n-dimensional representations, and second, because the combination of graphs with deep learning has shown a great performance in similar applications. Our methodology consists of: First, we will detect each isolated/atomic symbols (those that can not be decomposed in more graphical primitives) and the primitives that form a musical symbol. Then, we will build the graph taking as root node the notehead and as leaves those primitives or symbols that modify the note’s rhythm (stem, beam, flag) or pitch (flat, sharp, natural). Finally, the graph is translated into a human-readable character sequence for a final transcription and evaluation. Our method has been tested on more than five thousand measures, showing promising results.

Abstract: Scene Text Visual Question Answering (ST-VQA) has recently emerged as a hot research topic in Computer Vision. Current ST-VQA models have a big potential for many types of applications but lack the ability to perform well on more than one language at a time due to the lack of multilingual data, as well as the use of monolingual word embeddings for training. In this work, we explore the possibility to obtain bilingual and multilingual VQA models. In that regard, we use an already established VQA model that uses monolingual word embeddings as part of its pipeline and substitute them by FastText and BPEmb multilingual word embeddings that have been aligned to English. Our experiments demonstrate that it is possible to obtain bilingual and multilingual VQA models with a minimal loss in performance in languages not used during training, as well as a multilingual model trained in multiple languages that match the performance of the respective monolingual baselines.