This study provides a comprehensive review of the current state of the sign language processing (SLP) field, encompassing sign language recognition (SLR), translation (SLT), production (SLPn), and the associated datasets (SLD). It analyzes the advancements and challenges in each area, highlighting key methodologies and technologies. The authors explore feature extraction techniques, model architectures, and multimodal data integration in SLR. For SLT , they examine neural machine translation and sequence-to-sequence frameworks, emphasizing the need for context-aware systems. In SLPn, they review avatar-based systems and motion capture techniques, identifying gaps in generating natural and expressive sign language. The survey of SLD evaluates existing datasets and underscores the importance of comprehensive data collection. It also discusses current SLP systems’ limitations and proposes future research directions to enhance accuracy, naturalness, and user-centric applications.

This paper presents a plan for preparing for changes in the business environment by analyzing and predicting business district data in Seoul. The COVID-19 pandemic and economic crisis caused by inflation have led to an increase in store closures and a decrease in sales, which has had a significant impact on commercial districts. The number of stores and sales are critical factors that directly affect the business environment and can help prepare for changes. This study conducted correlation analysis to extract factors related to the commercial district’s environment in Seoul and estimated the number of stores and sales based on these factors. Using the Kendaltau correlation coefficient, the study found that existing population and working population were the most influential factors. Linear regression, tensor decomposition, Factorization Machine, and deep neural network models were used to estimate the number of stores and sales, with the deep neural network model showing the best performance in RMSE and evaluation indicators. This study also predicted the number of stores and sales of the service industry in a specific area using the population prediction results of the neural prophet model. The study’s findings can help identify commercial district information and predict the number of stores and sales based on location, industry, and influencing factors, contributing to the revitalization of commercial districts.

Talking human face generation aims at synthesizing a natural human face that talks in correspondence to the given text or audio series. Implementing the recently developed Deep Learning(DL) methods such as Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN)s, Neural Rendering Fields (NeRF) for data generation, and talking human face generation has attracted significant research interest from academia and industry. They have been explored and exploited recently and have been used to address several problems in image processing and computer vision. Notwithstanding notable advancements, implementing them to real-world problems such as talking human face generation remains challenging. The generation of deepfakes created by the abovementioned methods would greatly promote many fascinating applications, including augmented reality, virtual reality, computer games, teleconferencing, virtual try-on, special movie effects, and avatars. This research reviews and discusses DL related methods, including CNN, GANs, NeRF, and their implementation in talking human face generation. We aim to analyze existing approaches regarding their implementation to talking face generation, investigate the related general problems, and highlight the open study issues. We also provide quantitative and qualitative evaluations of the existing research approaches in the related field.

Abstract Human pose estimation is one of the issues that have gained many benefits from using state-of-the-art deep learning-based models. Human pose, hand and mesh estimation is a significant problem that has attracted the attention of the computer vision community for the past few decades. A wide variety of solutions have been proposed to tackle the problem. Deep Learning-based approaches have been extensively studied in recent years and used to address several computer vision problems. However, it is sometimes hard to compare these methods due to their intrinsic difference. This paper extensively summarizes the current deep learning-based 2D and 3D human pose, hand and mesh estimation methods with a single or multi-person, single or double-stage methodology-based taxonomy. The authors aim to make every step in the deep learning-based human pose, hand and mesh estimation techniques interpretable by providing readers with a readily understandable explanation. The presented taxonomy has clearly illustrated current research on deep learning-based 2D and 3D human pose, hand and mesh estimation. Moreover, it also provided dataset and evaluation metrics for both 2D and 3DHPE approaches.

A patent is one of the essential indicators of new technologies and business processes, which becomes the main driving force of the companies and even the national competitiveness as well, that has recently been submitted and exploited in a large scale of quantities of information sources. Since the number of patent processing personnel, however, can hardly keep up with the increasing number of patents, and thus may have been worried about from deteriorating the quality of examinations. In this regard, the advancement of deep learning for the language processing capabilities has been developed significantly so that the prior art search by the deep learning models also can be accomplished for the labor-intensive and expensive patent document search tasks. The prior art search requires differentiation tasks, usually with the sheer volume of relevant documents; thus, the recall is much more important than the precision, which is the primary difference from the conventional search engines. This paper addressed a method to effectively handle the patent documents using BERT, one of the major deep learning-based language models. We proved through experiments that our model had outperformed the conventional approaches and the combinations of the key components with the recall value of up to '94.29%' from the real patent dataset.

In the current era of big data, high volumes of valuable information are available in collections of documents, the web, social networks, and high varieties of linked data. To search and retrieve useful information from these linked data, users often enter queries into information retrieval (IR) systems. Among the information retrieved by these systems, some information is relevant to the user queries (i.e., Interested to the users), but some is not. Moreover, some relevant information may not be retrieved by the systems. The effectiveness of these IR systems is often measured by metrics such as precision and recall. Most of the conventional IR systems (e.g., For web searches) aim to achieve high precision (i.e., High percentage of the retrieved information is relevant) at the price of low recall (i.e., Low percentage of the relevant information is retrieved). However, there are real-life situations (e.g., Patent searches) in which having high recall is desirable. In this paper, we present two high-recall IR systems. Results of our evaluation show the effectiveness of our systems in providing high-recall IR from linked big data.

As the overall size of the social networks has been exponentially expanding, the technological advance of efficient social networks search can flourish in the academic sphere, business corporations, and public institutions. Additionally, facing environmental upheaval in the field of information fusion and consilience, an effective development of various social network searches is gaining significance. In this research, we propose the use of the Maximum Reliable Tree algorithm that is newly developed based on a graph-based method, as a generic technique which facilitates effective social network search and that can be the most reliable social network search method for the promptly appearing smart phone technologies. We presented the method's excellence in performance by demonstrating core arguments in formal descriptions, and illustrating experimental results.

With advances in technology, mobile handheld devices-such as PDAs-have become very popular. In many real-life situations, users want to find structuring information using these mobile devices, which are convenient to use but have relatively limited resources. In this paper, we present a top-k structured mobile Web search engine. It uses a top-k adaptable search-tree method that utilizes hierarchical structure of hypermedia objects to effectively look for structuring information from the mobile Web model. The engine, which is implemented in the mobile environment, provides users with top-k adaptive Web search recommendations for mobile handheld devices.

Clustering is a viable technique to deal with the scaling issue for the web documents, which has been known for complicated combinatorial optimization problem. It is hard to develop a generally applicable optimal algorithm on the web document clustering and classification for which a simulated annealing algorithm is developed. The web document classification problem is addressed as the problem of best describing match between a web query and a hypothesized web object. The normalized term frequency and inverse document frequency coefficient is used as a measure of the match. Test beds are generated on-line during the search by transforming web sites. As a result, web sites can be clustered optimally in terms of keyword vectors of corresponding web documents.

Query relaxation is one of the crucial components for approximate query answering. Query relaxation has extensively been investigated in terms of categorical data; few studies, however, have been effectively established for both numerical and categorical data. In this article, we develop a query relaxation method by exploiting hierarchical quantified data abstraction, and a novel method is proposed to quantify the semantic distances between the categorical data so that the query conditions for categorical data are effectively relaxed. We additionally introduce query relaxation algorithms to modify the approximate queries into ordinary queries, which are followed by a series of examples to represent the modification process. Our method outperformed the conventional approaches for the various combinations of complex queries with respect to the cost model and the number of child nodes.

An Asynchronous Differential Join (ADJ) scheme that can maintain join-materialized views in a distributed environment is introduced. The efficiency of the asynchronous data replication can be enhanced by minimizing data to be sent to relevant sites. It also has an advantage in that the scheme prevents huge base tables from being locked by the remote requests through the utilization of differential files. Experimental results show that the faster the communication speed and the lesser the screening factor, the higher the total cost ratio.Request access from your librarian to read this article's full text.