Related papers: Mind the Gap: Analyzing Lacunae with Transformer-B…

Historical handwritten text recognition (HTR) is essential for unlocking the cultural and scholarly value of archival documents, yet digitization is often hindered by scarce transcriptions, linguistic variation, and highly diverse…

In the context of inverse problems $\bf y = Ax$, sparse recovery offers a powerful paradigm shift by enabling the stable solution of ill-posed or underdetermined systems through the exploitation of structure, particularly sparsity. Sparse…

Computed Tomography (CT) reconstruction is a fundamental component to a wide variety of applications ranging from security, to healthcare. The classical techniques require measuring projections, called sinograms, from a full 180$^\circ$…

We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera. Our method leverages the motion differences…

We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions, or adherent raindrops, from a short sequence of images captured by a moving camera. Our method leverages motion…

Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements. Dictionary or transform learning methods are useful in applications such as denoising, inpainting, and medical image…

Compared with flatbed scanners, portable smartphones provide more convenience for physical document digitization. However, such digitized documents are often distorted due to uncontrolled physical deformations, camera positions, and…

In this paper, we propose a novel method based on character sequence-to-sequence models to correct documents already processed with Optical Character Recognition (OCR) systems. The main contribution of this paper is a set of strategies to…

As advances in signature recognition have reached a new plateau of performance at around 2% error rate, it is interesting to investigate alternative approaches. The approach detailed in this paper looks at using Variational Auto-Encoders…

Image registration is an essential but challenging task in medical image computing, especially for echocardiography, where the anatomical structures are relatively noisy compared to other imaging modalities. Traditional (non-learning)…

Nanopore sequencing can read substantially longer sequences of nucleic acid molecules, called reads, than other sequencing methods, which has led to advances in genomic analysis such as the gapless human genome assembly. By analyzing the…

Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while…

Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data are heavily incomplete. We investigate whether shifting…

In order to apply Optical Character Recognition (OCR) to historical printings of Latin script fully automatically, we report on our efforts to construct a widely-applicable polyfont recognition model yielding text with a Character Error…

In this paper, a tool for detecting LLM AI text generation is developed based on the Transformer model, aiming to improve the accuracy of AI text generation detection and provide reference for subsequent research. Firstly the text is…

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Among other merits, Transformers are witnessed as capable of learning long-range…

Robust perception systems are essential for autonomous vehicle safety. To navigate in a complex urban environment, it is necessary precise sensors with reliable data. The task of understanding the surroundings is hard by itself; for…

Processing of missing data by modern neural networks, such as CNNs, remains a fundamental, yet unsolved challenge, which naturally arises in many practical applications, like image inpainting or autonomous vehicles and robots. While…

Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc. Most state-of-the-art algorithms rectify the input image into the normalized image, then treat the…