相关论文: FEDS -- Filtered Edit Distance Surrogate

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…

We propose a novel method for generating scene-aware training data for far-field automatic speech recognition. We use a deep learning-based estimator to non-intrusively compute the sub-band reverberation time of an environment from its…

Scene-text spotting is a task that predicts a text area on natural scene images and recognizes its text characters simultaneously. It has attracted much attention in recent years due to its wide applications. Existing research has mainly…

Surrogate model can replace the parametric full-order model (FOM) by an approximation model, which can significantly improve the efficiency of optimization design and reduce the complexity of engineering systems. However, due to limitations…

Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that…

RNN-T is currently considered the industry standard in ASR due to its exceptional WERs in various benchmark tests and its ability to support seamless streaming and longform transcription. However, its biggest drawback lies in the…

Recent efforts on scene text erasing have shown promising results. However, existing methods require rich yet costly label annotations to obtain robust models, which limits the use for practical applications. To this end, we study an…

Text spotting in natural scene images is of great importance for many image understanding tasks. It includes two sub-tasks: text detection and recognition. In this work, we propose a unified network that simultaneously localizes and…

Text driven diffusion models have shown remarkable capabilities in editing images. However, when editing 3D scenes, existing works mostly rely on training a NeRF for 3D editing. Recent NeRF editing methods leverages edit operations by…

Among various distance functions for graphs, graph and subgraph edit distances (GED and SED respectively) are two of the most popular and expressive measures. Unfortunately, exact computations for both are NP-hard. To overcome this…

Textual information in a captured scene plays an important role in scene interpretation and decision making. Though there exist methods that can successfully detect and interpret complex text regions present in a scene, to the best of our…

In recent years, significant progress has been made in scene text recognition by data-driven methods. However, due to the scarcity of annotated real-world data, the training of these methods predominantly relies on synthetic data. The…

The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine…

In many mechanistic medical, biological, physical and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs) can make simulations impractically slow. Biological models require 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…

We study a family of algorithms, which we refer to as local update methods, that generalize many federated learning and meta-learning algorithms. We prove that for quadratic objectives, local update methods perform stochastic gradient…

While scene text recognition techniques have been widely used in commercial applications, data privacy has rarely been taken into account by this research community. Most existing algorithms have assumed a set of shared or centralized…

Distantly supervised models are very popular for relation extraction since we can obtain a large amount of training data using the distant supervision method without human annotation. In distant supervision, a sentence is considered as a…

Fine-grained information on translation errors is helpful for the translation evaluation community. Existing approaches can not synchronously consider error position and type, failing to integrate the error information of both. In this…

Contour based scene text detection methods have rapidly developed recently, but still suffer from inaccurate frontend contour initialization, multi-stage error accumulation, or deficient local information aggregation. To tackle these…