Abstract: Existing work on DocVQA only considers single-page documents. However, in real applications documents are mostly composed of multiple pages that should be processed altogether. In this work, we propose a new multimodal hierarchical method Hi-VT5, that overcomes the limitations of current methods to process long multipage documents. In contrast to previous hierarchical methods that focus on different semantic granularity (He et al., 2021) or different subtasks (Zhou et al., 2022) used in image classification. Our method is a hierarchical transformer architecture where the encoder learns to summarize the most relevant information of every page and then, the decoder uses this summarized representation to generate the final answer, following a bottom-up approach. Moreover, due to the lack of multipage DocVQA datasets, we also introduce MP-DocVQA, an extension of SP-DocVQA where questions are posed over multipage documents instead of single pages. Through extensive experimentation, we demonstrate that Hi-VT5 is able, in a single stage, to answer the questions and provide the page that contains the answer, which can be used as a kind of explainability measure.

Abstract: This study introduces a novel, hand-drawn language designed to foster human-robot collaboration in wood stereotomy, central to carpentry and joinery professions. Based on skilled carpenters’ line and symbol etchings on timber, this language signifies the location, geometry of woodworking joints, and timber placement within a framework. A proof-of-concept prototype has been developed, integrating object detectors, keypoint regression, and traditional computer vision techniques to interpret this language and enable an extensive repertoire of actions. Empirical data attests to the language’s efficacy, with the successful identification of a specific set of symbols on various wood species’ sawn surfaces, achieving a mean average precision (mAP) exceeding 90%. Concurrently, the system can accurately pinpoint critical positions that facilitate robotic comprehension of carpenter-indicated woodworking joint geometry. The positioning error, approximately 3 pixels, meets industry standards.

Abstract: We consider a quantum system that is being continuously monitored, giving rise to a measurement signal. From such a stream of data, information needs to be inferred about the underlying system's dynamics. Here we focus on hypothesis testing problems and put forward the usage of sequential strategies where the signal is analyzed in real time, allowing the experiment to be concluded as soon as the underlying hypothesis can be identified with a certified prescribed success probability. We analyze the performance of sequential tests by studying the stopping-time behavior, showing a considerable advantage over currently-used strategies based on a fixed predetermined measurement time.

Abstract: This paper investigates the effectiveness of different deep learning HTR families, including LSTM, Seq2Seq, and transformer-based approaches with self-supervised pretraining, in recognizing ciphered manuscripts from different historical periods and cultures. The goal is to identify the most suitable method or training techniques for recognizing ciphered manuscripts and to provide insights into the challenges and opportunities in this field of research. We evaluate the performance of these models on several datasets of ciphered manuscripts and discuss their results. This study contributes to the development of more accurate and efficient methods for recognizing historical manuscripts for the preservation and dissemination of our cultural heritage.

Abstract: Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, where data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance on English, Italian and Russian scripts, whilst adding only a few parameters per task. The code and trained models will be publicly available.

Abstract: Global visual localization estimates the absolute pose of a camera using a single image, in a previously mapped area. Obtaining the pose from a single image enables many robotics and augmented/virtual reality applications. Inspired by latest advances in deep learning, many existing approaches directly learn and regress 6 DoF pose from an input image. However, these methods do not fully utilize the underlying scene geometry for pose regression. The challenge in monocular relocalization is the minimal availability of supervised training data, which is just the corresponding 6 DoF poses of the images. In this letter, we propose to utilize these minimal available labels (i.e., poses) to learn the underlying 3D geometry of the scene and use the geometry to estimate the 6 DoF camera pose. We present a learning method that uses these pose labels and rigid alignment to learn two 3D geometric representations ( X, Y, Z coordinates ) of the scene, one in camera coordinate frame and the other in global coordinate frame. Given a single image, it estimates these two 3D scene representations, which are then aligned to estimate a pose that matches the pose label. This formulation allows for the active inclusion of additional learning constraints to minimize 3D alignment errors between the two 3D scene representations, and 2D re-projection errors between the 3D global scene representation and 2D image pixels, resulting in improved localization accuracy. During inference, our model estimates the 3D scene geometry in camera and global frames and aligns them rigidly to obtain pose in real-time. We evaluate our work on three common visual localization datasets, conduct ablation studies, and show that our method exceeds state-of-the-art regression methods' pose accuracy on all datasets.