Related papers: I2C2W: Image-to-Character-to-Word Transformers for…
Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape.…
Scene text detection and recognition has received increasing research attention. Existing methods can be roughly categorized into two groups: character-based and segmentation-based. These methods either are costly for character annotation…
Recognizing scene text is a challenging problem, even more so than the recognition of scanned documents. This problem has gained significant attention from the computer vision community in recent years, and several methods based on energy…
Recent end-to-end scene text spotters have achieved great improvement in recognizing arbitrary-shaped text instances. Common approaches for text spotting use region of interest pooling or segmentation masks to restrict features to single…
Natural scene character recognition is challenging due to the cluttered background, which is hard to separate from text. In this paper, we propose a novel method for robust scene character recognition. Specifically, we first use robust…
Recently, transformer-based methods have achieved promising progresses in object detection, as they can eliminate the post-processes like NMS and enrich the deep representations. However, these methods cannot well cope with scene text due…
It is crucial to understand the robustness of text detection models with regard to extensive corruptions, since scene text detection techniques have many practical applications. For systematically exploring this problem, we propose two…
Inspired by the success of Deep Learning based approaches to English scene text recognition, we pose and benchmark scene text recognition for three Indic scripts - Devanagari, Telugu and Malayalam. Synthetic word images rendered from…
Forecasting the evolution of 3D scenes and generating unseen scenarios via occupancy-based world models offers substantial potential for addressing corner cases in autonomous driving systems. While tokenization has revolutionized image and…
Recent advances in language and vision push forward the research of captioning a single image to describing visual differences between image pairs. Suppose there are two images, I_1 and I_2, and the task is to generate a description W_{1,2}…
Multi-modal models have shown appealing performance in visual recognition tasks, as free-form text-guided training evokes the ability to understand fine-grained visual content. However, current models cannot be trivially applied to scene…
In recent years, recognition of text from natural scene image and video frame has got increased attention among the researchers due to its various complexities and challenges. Because of low resolution, blurring effect, complex background,…
Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage framework by involving ROI pooling, which can degrade the…
Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…
Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…
This paper discusses the challenges of optical character recognition (OCR) on natural scenes, which is harder than OCR on documents due to the wild content and various image backgrounds. We propose to uniformly use word error rates (WER) as…
Despite the longstanding adage "an image is worth a thousand words," generating accurate hyper-detailed image descriptions remains unsolved. Trained on short web-scraped image text, vision-language models often generate incomplete…
An unconstrained end-to-end text localization and recognition method is presented. The method detects initial text hypothesis in a single pass by an efficient region-based method and subsequently refines the text hypothesis using a more…
Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i.e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse…
Reading text from natural images is challenging due to the great variety in text font, color, size, complex background and etc.. The perspective distortion and non-linear spatial arrangement of characters make it further difficult. While…