Related papers: Towards the Unseen: Iterative Text Recognition by …
The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…
In autonomous driving tasks, scene understanding is the first step towards predicting the future behavior of the surrounding traffic participants. Yet, how to represent a given scene and extract its features are still open research…
Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…
In this work we present a state-of-the-art approach for unconstrained natural scene text recognition. We propose a cascade approach that incorporates a convolutional neural network (CNN) architecture followed by a long short term memory…
Scene text detection is an important step of scene text reading system. The main challenges lie on significantly varied sizes and aspect ratios, arbitrary orientations and shapes. Driven by recent progress in deep learning, impressive…
Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing…
The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then it is tested on unseen examples that belong to one of the…
Text detection, the key technology for understanding scene text, has become an attractive research topic. For detecting various scene texts, researchers propose plenty of detectors with different advantages: detection-based models enjoy…
Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the…
Text recognition in the wild is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest vision and language processing are effective for scene text recognition. Yet, solving edit errors such as…
Text detection is frequently used in vision-based mobile robots when they need to interpret texts in their surroundings to perform a given task. For instance, delivery robots in multilingual cities need to be capable of doing multilingual…
Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than purely text-driven approaches. However, existing diffusion transformer-based methods…
Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural…
Text-to-image retrieval is a fundamental task in multimedia processing, aiming to retrieve semantically relevant cross-modal content. Traditional studies have typically approached this task as a discriminative problem, matching the text and…
People typically learn through exposure to visual concepts associated with linguistic descriptions. For instance, teaching visual object categories to children is often accompanied by descriptions in text or speech. In a machine learning…
Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge. However, vast majority of the existing methods detect text within local…
Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…
Generating images with embedded text is crucial for the automatic production of visual and multimodal documents, such as educational materials and advertisements. However, existing diffusion-based text-to-image models often struggle to…
Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the…
Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…