The digitization of historical manuscripts has significantly advanced in recent decades, yet many documents remain as images without machine-readable text. Handwritten Text Recognition (HTR) has emerged as a crucial tool for converting these images into text, facilitating large-scale analysis of historical collections. In 2024, the CATMuS Medieval ...
Recent advancements in handwritten text recognition (HTR) for historical documents have demonstrated high performance on cursive Arabic scripts, achieving accuracy comparable to Latin scripts. The initial RASAM dataset, focused on three Arabic Maghribi manuscripts, facilitated rapid coverage of new documents via fine-tuning. However, HTR applicatio...
Annotating 3D medical images demands expert knowledge and is time-consuming. As a result, semi-supervised learning (SSL) approaches have gained significant interest in 3D medical image segmentation. The significant size differences among various organs in the human body lead to imbalanced class distribution, which is a major challenge in the real-w...
Vision Transformers (ViTs) have shown promising results in computer vision tasks, challenging CNN architectures on image classification, segmentation and object detection. However, their quadratic complexity O(N 2 ), where N is the token sequence length, hinders their deployment on edge devices. To tackle this challenge, researchers have proposed v...
This work deals with image generation, two main problems are addressed: (i ) improvements of specific feature extraction while accounting at multiscale levels intrinsic geometric features, and (ii ) equivariance of the network for reducing the complexity and providing a geometric interpretability. We propose a geometric generative model based on an...
Image classification -or semantic segmentation -from input multiresolution imagery is a demanding task. In particular, when dealing with images of the same scene collected at the same time by very different acquisition systems, for example multispectral sensors onboard satellites and unmanned aerial vehicles (UAVs), the difference between the invol...
Despite the extensive body of literature focused on remote sensing applications for land cover mapping and the availability of high-resolution satellite imagery, methods for continuously updating classification maps in real-time remain limited, especially when training data is scarce. This paper introduces the recursive Bayesian classifier (RBC), w...
Hyperspectral image (HSI) classification plays a critical role in various practical applications, including precision agriculture, environmental monitoring, and urban planning, where accurate identification of materials based on their spectral signatures is essential. However, the high dimensionality of hyperspectral data poses significant challeng...
While much effort has been invested in generating human motion from text, relatively few studieshave been dedicated to the reverse direction, that is, generating text from motion. Much of theresearch focuses on maximizing generation quality without any regard for the interpretability of thearchitectures, particularly regarding the influence of part...
Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data modalities. Traditional approaches for CMKD are based on a teacher/student paradigm where a teacher is trained on...
