Related papers: Scene Text Recognition with Semantics

Employing a dictionary can efficiently rectify the deviation between the visual prediction and the ground truth in scene text recognition methods. However, the independence of the dictionary on the visual features may lead to incorrect…

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…

Many tasks are related to determining if a particular text string exists in an image. In this work, we propose a new framework that learns this task in an end-to-end way. The framework takes an image and a text string as input and then…

Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to…

Recognizing a traffic accident is an essential part of any autonomous driving or road monitoring system. An accident can appear in a wide variety of forms, and understanding what type of accident is taking place may be useful to prevent it…

Scene understanding is a popular and challenging topic in both computer vision and photogrammetry. Scene graph provides rich information for such scene understanding. This paper presents a novel approach to infer such relations and then to…

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Segmentation-based methods are widely used for scene text detection due to their superiority in describing arbitrary-shaped text instances. However, two major problems still exist: 1) current label generation techniques are mostly empirical…

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…

Scene text recognition (STR) methods have struggled to attain high accuracy and fast inference speed. Autoregressive (AR)-based models implement the recognition in a character-by-character manner, showing superiority in accuracy but with…

Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR), especially where training and testing data reside in different domains. The efficacy of existing UDA approaches tends to degrade when…

Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the…

The recognition of texts existing in camera-captured images has become an important issue for a great deal of research during the past few decades. This give birth to Scene Character Recognition (SCR) which is an important step in scene…

Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction. In this paper, we propose a Spatial-Temporal Semantic Consistency method to…

The open-set text recognition task is an emerging challenge that requires an extra capability to cognize novel characters during evaluation. We argue that a major cause of the limited performance for current methods is the confounding…

Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character…

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Recent works in the text recognition area have pushed forward the recognition results to the new horizons. But for a long time a lack of large human-labeled natural text recognition datasets has been forcing researchers to use synthetic…