Related papers: Autonomous Cleaning of Corrupted Scanned Documents…

We present a generative document-specific approach to character analysis and recognition in text lines. Our main idea is to build on unsupervised multi-object segmentation methods and in particular those that reconstruct images based on a…

The performance of graph representation learning is affected by the quality of graph input. While existing research usually pursues a globally smoothed graph embedding, we believe the rarely observed anomalies are as well harmful to an…

Processing large amounts of data is an essential problem of the big data era. Most of the data exchange is done via direct communication (using APIs) and well-structured file formats (JSON, XML, EDI, etc.), but a significant portion of the…

Document denoising is considered one of the most challenging tasks in computer vision. There exist millions of documents that are still to be digitized, but problems like document degradation due to natural and man-made factors make this…

Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world. In spite of such advances, a higher level understanding of vision and imagery…

Detecting tampered text in document images is a challenging task due to data scarcity. To address this, previous work has attempted to generate tampered documents using rule-based methods. However, the resulting documents often suffer from…

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

Label noise in real-world datasets encodes wrong correlation patterns and impairs the generalization of deep neural networks (DNNs). It is critical to find efficient ways to detect corrupted patterns. Current methods primarily focus on…

Significant work has been done on learning regular expressions from a set of data values. Depending on the domain, this approach can be very successful. However, significant time is required to learn these expressions and the resulting…

OCR errors are common in digitised historical archives significantly affecting their usability and value. Generative Language Models (LMs) have shown potential for correcting these errors using the context provided by the corrupted text and…

Plagiarism is an act of using someone else's work without proper acknowledgment, and this sin is seen to cut across various arenas including the academy, publishing, and other similar arenas. The traditional methods of plagiarism detection…

The outcome of text recognition for degraded color documents is often unsatisfactory due to interference from various contaminants. To extract information more efficiently for text recognition, document image enhancement and binarization…

In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual…

We propose a deep and interpretable probabilistic generative model to analyze glyph shapes in printed Early Modern documents. We focus on clustering extracted glyph images into underlying templates in the presence of multiple confounding…

We propose a deep factorization model for typographic analysis that disentangles content from style. Specifically, a variational inference procedure factors each training glyph into the combination of a character-specific content embedding…

Document editing has become a pervasive component of the production of information, with version control systems enabling edits to be efficiently stored and applied. In light of this, the task of learning distributed representations of…

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to…

We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined inter-layer feature links. By using a data-free cosine…

Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric…

Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor…