It is challenging to detect arbitrary-shape text accurately and effectively in natural scenes. While many methods have been implemented for arbitrary-shape text detection, most cannot achieve ...real-time detection or meet practical needs. In this work, we propose a YOLOv6-based detector that can effectively implement arbitrary-shape text detection and achieve real-time detection. We include two additional branches in the neck part of the YOLOv6 network to adapt the network to text detection, and the output side uses the pixel aggregation (PA) algorithm to decouple the PA output to use it as the detection head of the model. Experiments on benchmark Total-Text, CTW1500, ICDAR2015, and MSRA-TD500 showed that the proposed method outperformed competing methods in terms of detection accuracy and running time. Specifically, our method achieved an F-measure of 84.1% at 291.8 FPS for 640 × 640 Total-Text images and an F-measure of 81.5% at 199.6 FPS for 896 × 896 ICDAR2015 incidental text images.
Digital spaces are saturated with metaphor: we have pages, sites, mice, and windows. Yet, in the world of digital textuality, these metaphors no longer function as we might expect. Martin Paul Eve ...calls attention to the digital-textual metaphors that condition our experience of digital space, and traces their history as they interact with physical cultures. Eve posits that digital-textual metaphors move through three life phases. Initially they are descriptive. Then they encounter a moment of fracture or rupture. Finally, they go on to have a prescriptive life of their own that conditions future possibilities for our text environments—even when the metaphors have become untethered from their original intent. Why is ""whitespace"" white? Was the digital page always a foregone conclusion? Over a series of theses, Eve addresses these and other questions in order to understand the moments when digital-textual metaphors break and to show us how it is that our textual softwares become locked into paradigms that no longer make sense. Contributing to book history, literary studies, new media studies, and material textual studies, Theses on the Metaphors of Digital-Textual History provides generative insights into the metaphors that define our digital worlds.
Effective collaboration in computer-mediated settings among spatially distributed people is a precondition for success in many new learning and working contexts but it is hard to achieve. We have ...developed two instructional approaches to improve collaboration in such settings by promoting people's capabilities to collaborate in a fruitful way and furthering their understanding of what characterizes good collaboration. The rationale is that strategies necessary for a good and effective computer-mediated collaboration may be conveyed to people by exposing them to an elaborated worked-out collaboration example (observational learning) or by giving them the opportunity to learn from scripted collaborative problem-solving. An experimental study was conducted that compared learning from observing a worked-out collaboration example with the learning effects of scripted collaborative problem-solving, the effects of unscripted collaborative problem-solving, and a control condition without a learning phase. The experimental design provided clearly separated phases for the instructional treatments (learning phase) and for applying and testing the acquired skills (application phase). Both observing a worked-out collaboration example and collaborating with a script during the learning phase showed positive effects on process and outcome of the second collaboration in the application phase.
The encoder–decoder architecture is a well-established, effective and widely used approach in many tasks of natural language processing (NLP), among other domains. It consists of two ...closely-collaborating components: An encoder that transforms the input into an intermediate form, and a decoder producing the output. This paper proposes a new method for the encoder, named Causal Feature Extractor (CFE), based on three main ideas: Causal convolutions, dilatations and bidirectionality. We apply this method to text normalization, which is a ubiquitous problem that appears as the first step of many text-to-speech (TTS) systems. Given a text with symbols, the problem consists in writing the text exactly as it should be read by the TTS system. We make use of an attention-based encoder–decoder architecture using a fine-grained character-level approach rather than the usual word-level one. The proposed CFE is compared to other common encoders, such as convolutional neural networks (CNN) and long-short term memories (LSTM). Experimental results show the feasibility of CFE, achieving better results in terms of accuracy, number of parameters, convergence time, and use of an attention mechanism based on attention matrices. The obtained accuracy ranges from 83.5% to 96.8% correctly normalized sentences, depending on the dataset. Moreover, the proposed method is generic and can be applied to different types of input such as text, audio and images.
Mastering Vim will introduce you to the wonderful world of Vim by example of working with Python code and tools in a project-based fashion. This book will prompt you to make Vim your primary IDE as ...you will learn to use it for any programming language.
Track Changes Kirschenbaum, Matthew G
2016, 2016-05-02, 2016-01-01
eBook
Writing in the digital age has been as messy as the inky rags in Gutenberg's shop or the molten lead of a Linotype machine. Matthew Kirschenbaum examines how creative authorship came to coexist with ...the computer revolution. Who were the early adopters, and what made others anxious? Was word processing just a better typewriter, or something more?.
Reading is an integral part of life in today's information-driven societies. Since the pioneering work of Dejerine on "word blindness" in brain-lesioned patients, the literature has increased ...exponentially, from neuropsychological case reports to mechanistic accounts of word processing at the behavioural, neurofunctional and computational levels, tapping into diverse aspects of visual word processing. These studies have revealed some exciting findings about visual word processing, including how the brain learns to read, how changes in literacy impact upon word processing strategies, and whether word processing mechanisms vary across different alphabetic, logographic or artificial writing systems. Other studies have attempted to characterise typical and atypical word processes in special populations in order to explain why dyslexic brains struggle with words, how multilingualism changes the way our brains see words, and what the exact developmental signatures are that would shape the acquisition of reading skills. Exciting new insights have also emerged from recent studies that have investigated word stimuli at the system/network level, by looking for instance, at how the reading system interacts with other cognitive systems in a context-dependent fashion, how visual language stimuli are integrated into the speech processing streams, how both left and right hemispheres cooperate and interact during word processing, and what the exact contributions of subcortical and cerebellar regions to reading are. The contributions to this Research Topic highlight the latest findings regarding the different issues mentioned above, particularly how these findings can explain or model the different processes, mechanisms, pathways or cognitive strategies by which the human brain sees words. The introductory editorial, summarising the contributions included here, highlights how varieties of behavioural tests and neuroimaging techniques can be used to investigate word processing mechanisms across different alphabetic and logographic writing systems.
PDF
