Abstract: The Human Pose Recovery and Behaviour Analysis group (HuPBA), University of Barcelona, is developing a line of research on multi-modal analysis of humans in visual data. The novel technology is being applied in several scenarios with high social impact, including sign language recognition, assisted technology and supported diagnosis for the elderly and people with mental/physical disabilities, fitness conditioning, and Human Computer Interaction.

Abstract: Many real problems require multi-class decisions. In the Pattern Recognition field,
many techniques have been proposed to deal with the binary problem. However,
the extension of many 2-class classifiers to the multi-class case is a hard task. In
this sense, Error-Correcting Output Codes (ECOC) demonstrated to be a powerful
tool to combine any number of binary classifiers to model multi-class problems. But
there are still many open issues about the capabilities of the ECOC framework. In
this thesis, the two main stages of an ECOC design are analyzed: the coding and
the decoding steps. We present different problem-dependent designs. These designs
take advantage of the knowledge of the problem domain to minimize the number
of classifiers, obtaining a high classification performance. On the other hand, we
analyze the ECOC codification in order to define new decoding rules that take full
benefit from the information provided at the coding step. Moreover, as a successful
classification requires a rich feature set, new feature detection/extraction techniques
are presented and evaluated on the new ECOC designs. The evaluation of the new
methodology is performed on different real and synthetic data sets: UCI Machine
Learning Repository, handwriting symbols, traffic signs from a Mobile Mapping System, Intravascular Ultrasound images, Caltech Repository data set or Chaga’s disease
data set. The results of this thesis show that significant performance improvements
are obtained on both traditional coding and decoding ECOC designs when the new
coding and decoding rules are taken into account.

Abstract: Visual data obtained during driving scenarios usually contain large amounts of text that conveys semantic information necessary to analyse the urban environment and is integral to the traffic control plan. Yet, research on autonomous driving or driver assistance systems typically ignores this information. To advance research in this direction, we present RoadText-3K, a large driving video dataset with fully annotated text. RoadText-3K is three times bigger than its predecessor and contains data from varied geographical locations, unconstrained driving conditions and multiple languages and scripts. We offer a comprehensive analysis of tracking by detection and detection by tracking methods exploring the limits of state-of-the-art text detection. Finally, we propose a new end-to-end trainable tracking model that yields state-of-the-art results on this challenging dataset. Our experiments demonstrate the complexity and variability of RoadText-3K and establish a new, realistic benchmark for scene text tracking in the wild.

Abstract: We introduce the structured scene-text spotting task, which requires a scene-text OCR system to spot text in the wild according to a query regular expression. Contrary to generic scene text OCR, structured scene-text spotting seeks to dynamically condition both scene text detection and recognition on user-provided regular expressions. To tackle this task, we propose the Structured TExt sPotter (STEP), a model that exploits the provided text structure to guide the OCR process. STEP is able to deal with regular expressions that contain spaces and it is not bound to detection at the word-level granularity. Our approach enables accurate zero-shot structured text spotting in a wide variety of real-world reading scenarios and is solely trained on publicly available data. To demonstrate the effectiveness of our approach, we introduce a new challenging test dataset that contains several types of out-of-vocabulary structured text, reflecting important reading applications of fields such as prices, dates, serial numbers, license plates etc. We demonstrate that STEP can provide specialised OCR performance on demand in all tested scenarios.

Abstract: Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural Radiance Fields (NeRF) have achieved impressive results. However no prior works investigate 3D-aware GANs for 3D consistent multiclass image-to-image (3D-aware 121) translation. Naively using 2D-121 translation methods suffers from unrealistic shape/identity change. To perform 3D-aware multiclass 121 translation, we decouple this learning process into a multiclass 3D-aware GAN step and a 3D-aware 121 translation step. In the first step, we propose two novel techniques: a new conditional architecture and an effective training strategy. In the second step, based on the well-trained multiclass 3D-aware GAN architecture, that preserves view-consistency, we construct a 3D-aware 121 translation system. To further reduce the view-consistency problems, we propose several new techniques, including a U-net-like adaptor network design, a hierarchical representation constrain and a relative regularization loss. In exten-sive experiments on two datasets, quantitative and qualitative results demonstrate that we successfully perform 3D-aware 121 translation with multi-view consistency. Code is available in 3DI2I.

Abstract: In this article, a system to detect rooms in architectural floor plan images is described. We first present a primitive extraction algorithm for line detection. It is based on an original coupling of classical Hough transform with image vectorization in order to perform robust and efficient line detection. We show how the lines that satisfy some graphical arrangements are combined into walls. We also present the way we detect some door hypothesis thanks to the extraction of arcs. Walls and door hypothesis are then used by our room segmentation strategy; it consists in recursively decomposing the image until getting nearly convex regions. The notion of convexity is difficult to quantify, and the selection of separation lines between regions can also be rough. We take advantage of knowledge associated to architectural floor plans in order to obtain mostly rectangular rooms. Qualitative and quantitative evaluations performed on a corpus of real documents show promising results.