Related papers: Quantifying Character Similarity with Vision Trans…
Handwritten text recognition aims to convert visual input into machine-readable text, and it remains challenging due to the evolving and context-dependent nature of handwriting. Character sets change over time, and character frequency…
Inspired by the tremendous success of the self-attention mechanism in natural language processing, the Vision Transformer (ViT) creatively applies it to image patch sequences and achieves incredible performance. However, the scaled…
Detecting manipulations in digital documents is becoming increasingly important for information verification purposes. Due to the proliferation of image editing software, altering key information in documents has become widely accessible.…
The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited…
Despite the significant success in the field of text recognition, complex and unsolved problems still exist in this field. In recent years, the recognition accuracy of the English language has greatly increased, while the problem of…
Language is far more than a communication tool. A wealth of information - including but not limited to the identities, psychological states, and social contexts of its users - can be gleaned through linguistic markers, and such insights are…
Measuring similarities between strings is central for many established and fast growing research areas including information retrieval, biology, and natural language processing. The traditional approach for string similarity measurements is…
Vision-language models (VLMs) can read text from images, but where does this optical character recognition (OCR) information enter the language processing stream? We investigate the OCR routing mechanism across three architecture families…
Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these…
Optical Character Recognition (OCR) is one of the important fields in image processing and pattern recognition domain. Handwritten character recognition has always been a challenging task. Only a little work can be traced towards the…
Large Language Models (LLMs) struggle with long-context code due to window limitations. Existing textual code compression methods mitigate this via selective filtering but often disrupt dependency closure, causing semantic fragmentation. To…
Diacritic characters can be considered as a unique set of characters providing us with adequate and significant clue in identifying a given language with considerably high accuracy. Diacritics, though associated with phonetics often serve…
Person re-identification aims to maintain the identity of an individual in diverse locations through different non-overlapping camera views. The problem is fundamentally challenging due to appearance variations resulting from differing…
The edit distance is a fundamental measure of sequence similarity, defined as the minimum number of character insertions, deletions, and substitutions needed to transform one string into the other. Given two strings of length at most $n$,…
Standard OCR is a well-researched topic of computer vision and can be considered solved for machine-printed text. However, when applied to unconstrained images, the recognition rates drop drastically. Therefore, the employment of object…
Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the…
For the bachelor project 2021 of Professor Lippert's research group, handwritten entries of historical patient records needed to be digitized using Optical Character Recognition (OCR) methods. Since the data will be used in the future, a…
Graph contrastive learning (GCL) has achieved remarkable success by following the computer vision paradigm of preserving absolute similarity between augmented views. However, this approach faces fundamental challenges in graphs due to their…
This thesis employs a hybrid CNN-Transformer architecture, alongside a detailed anthropological framework, to investigate potential historical connections between the visual morphology of the Indus Valley script and pictographic systems of…
Most discrete visual tokenizers rely on a default design: every position in the sequence shares the same codebook. Researchers try to scale the codebook size $K$ to get better reconstruction performance. Such a constant-codebook design hits…