Abstract: Detecting pedestrians with on-board vision systems is of paramount interest for assisting drivers to prevent vehicle-to-pedestrian accidents. The core of a pedestrian detector is its classification module, which aims at deciding if a given image window contains a pedestrian. Given the difficulty of this task, many classifiers have been proposed during the last fifteen years. Among them, the so-called (deformable) part-based classifiers including multi-view modeling are usually top ranked in accuracy. Training such classifiers is not trivial since a proper aspect clustering and spatial part alignment of the pedestrian training samples are crucial for obtaining an accurate classifier. In this paper, first we perform automatic aspect clustering and part alignment by using virtual-world pedestrians, i.e., human annotations are not required. Second, we use a mixture-of-parts approach that allows part sharing among different aspects. Third, these proposals are integrated in a learning framework which also allows to incorporate real-world training data to perform domain adaptation between virtual- and real-world cameras. Overall, the obtained results on four popular on-board datasets show that our proposal clearly outperforms the state-of-the-art deformable part-based detector known as latent SVM.

Abstract: Detecting hands in multi-modal RGB-Depth visual data has become a challenging Computer Vision problem with several applications of interest. This task involves dealing with changes in illumination, viewpoint variations, the articulated nature of the human body, the high flexibility of the wrist articulation, and the deformability of the hand itself. In this work, we propose an accurate and efficient automatic hand detection scheme to be applied in Human-Computer Interaction (HCI) applications in which the user is seated at the desk and, thus, only the upper body is visible. Our main hypothesis is that hand landmarks remain at a nearly constant geodesic distance from an automatically located anatomical reference point.
In a given frame, the human body is segmented first in the depth image. Then, a
graph representation of the body is built in which the geodesic paths are computed from the reference point. The dense optical flow vectors on the corresponding RGB image are used to reduce ambiguities of the geodesic paths’ connectivity, allowing to eliminate false edges interconnecting different body parts. Finally, we are able to detect the position of both hands based on invariant geodesic distances and optical flow within the body region, without involving costly learning procedures.

Abstract: Despite the outperformance of Support Vector Machine (SVM) on many practical classification problems, the algorithm is not directly applicable to multi-dimensional trajectories having different lengths. In this paper, a new class of SVM that is applicable to trajectory classification, such as action recognition, is developed by incorporating two efficient time-series distances measures into the kernel function.
Dynamic Time Warping and Longest Common Subsequence distance measures along with their derivatives are
employed as the SVM kernel. In addition, the pairwise proximity learning strategy is utilized in order to make use of non-positive semi-definite kernels in the SVM formulation. The proposed method is employed for a challenging classification problem: action recognition by depth cameras using only skeleton data; and evaluated on three benchmark action datasets. Experimental results demonstrate the outperformance of our methodology compared to the state-ofthe-art on the considered datasets.

Abstract: Despite the latest advances in Deep Learning, the recognition of handwritten music scores is still a challenging endeavour. Even though the recent Sequence to Sequence(Seq2Seq) architectures have demonstrated its capacity to reliably recognise handwritten text, their performance is still far from satisfactory when applied to historical handwritten scores. Indeed, the ambiguous nature of handwriting, the non-standard musical notation employed by composers of the time and the decaying state of old paper make these scores remarkably difficult to read, sometimes even by trained humans. Thus, in this work we explore the incorporation of language models into a Seq2Seq-based architecture to try to improve transcriptions where the aforementioned unclear writing produces statistically unsound mistakes, which as far as we know, has never been attempted for this field of research on this architecture. After studying various Language Model integration techniques, the experimental evaluation on historical handwritten music scores shows a significant improvement over the state of the art, showing that this is a promising research direction for dealing with such difficult manuscripts.

Abstract: Despite the “paperless office” ideal that started in the decade of the seventies, businesses still strive against an increasing amount of paper documentation. Companies still receive huge amounts of paper documentation that need to be analyzed and processed, mostly in a manual way. A solution for this task consists in, first, automatically scanning the incoming documents. Then, document images can be analyzed and information can be extracted from the data. Documents can also be automatically dispatched to the appropriate workflows, used to retrieve similar documents in the dataset to transfer information, etc.
Due to the nature of this “digital mailroom”, we need document representation methods to be general, i.e., able to cope with very different types of documents. We need the methods to be sound, i.e., able to cope with unexpected types of documents, noise, etc. And, we need to methods to be scalable, i.e., able to cope with thousands or millions of documents that need to be processed, stored, and consulted. Unfortunately, current techniques of document representation, classification and retrieval are not apt for this digital mailroom framework, since they do not fulfill some or all of these requirements.
Through this thesis we focus on the problem of document representation aimed at classification and retrieval tasks under this digital mailroom framework. We first propose a novel document representation based on runlength histograms, and extend it to cope with more complex documents such as multiple-page documents, or documents that contain more sources of information such as extracted OCR text. Then we focus on the scalability requirements and propose a novel binarization method which we dubbed PCAE, as well as two general asymmetric distances between binary embeddings that can significantly improve the retrieval results at a minimal extra computational cost. Finally, we note the importance of supervised learning when performing large-scale retrieval, and study several approaches that can significantly boost the results at no extra cost at query time.

Abstract: Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to automatically synthesize document images based on a given layout. In this work, given a spatial layout (bounding boxes with object categories) as a reference by the user, our proposed DocSynth model learns to generate a set of realistic document images consistent with the defined layout. Also, this framework has been adapted to this work as a superior baseline model for creating synthetic document image datasets for augmenting real data during training for document layout analysis tasks. Different sets of learning objectives have been also used to improve the model performance. Quantitatively, we also compare the generated results of our model with real data using standard evaluation metrics. The results highlight that our model can successfully generate realistic and diverse document images with multiple objects. We also present a comprehensive qualitative analysis summary of the different scopes of synthetic image generation tasks. Lastly, to our knowledge this is the first work of its kind.

Abstract: Despite recent significant advances, pedestrian detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities and a strong multi-view classifier that accounts for different pedestrian views and poses. In this paper we provide an extensive evaluation that gives insight into how each of these aspects (multi-cue, multimodality and strong multi-view classifier) affect performance both individually and when integrated together. In the multimodality component we explore the fusion of RGB and depth maps obtained by high-definition LIDAR, a type of modality that is only recently starting to receive attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the performance, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient. These simple blocks can be easily replaced with more sophisticated ones recently proposed, such as the use of convolutional neural networks for feature representation, to further improve the accuracy.

Abstract: Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text Recognition (HTR) models. The Keyword Spotting System (KWS) provides a valid alternative to HTR due to the reduction in error rate, but it is usually limited to a closed reference vocabulary. In this paper, we propose a few-shot learning paradigm for spotting sequences of a few characters (N-gram) that requires a small amount of labelled training data. We exhibit that recognition of important n-grams could reduce the system’s dependency on vocabulary. In this case, an out-of-vocabulary (OOV) word in an input handwritten line image could be a sequence of n-grams that belong to the lexicon. An extensive experimental evaluation of our proposed multi-representation approach was carried out on a subset of Bentham’s historical manuscript collections to obtain some really promising results in this direction.