• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.293-310
• /
• 2024

In this paper, we propose an agent model for Language-Driven Zero-Shot Object Navigation (L-ZSON) tasks, which takes in a freeform language description of an unseen target object and navigates to find out the target object in an inexperienced environment. In general, an L-ZSON agent should able to visually ground the target object by understanding the freeform language description of it and recognizing the corresponding visual object in camera images. Moreover, the L-ZSON agent should be also able to build a rich spatial context map over the unknown environment and decide efficient exploration actions based on the map until the target object is present in the field of view. To address these challenging issues, we proposes AML (Agent Model for L-ZSON), a novel L-ZSON agent model to make effective use of AI foundation models such as Large Language Model (LLM) and Vision-Language model (VLM). In order to tackle the visual grounding issue of the target object description, our agent model employs GLEE, a VLM pretrained for locating and identifying arbitrary objects in images and videos in the open world scenario. To meet the exploration policy issue, the proposed agent model leverages the commonsense knowledge of LLM to make sequential navigational decisions. By conducting various quantitative and qualitative experiments with RoboTHOR, the 3D simulation platform and PASTURE, the L-ZSON benchmark dataset, we show the superior performance of the proposed agent model.

• Journal of information and communication convergence engineering
• /
• v.8 no.1
• /
• pp.19-22
• /
• 2010

A finger language helping hearing impaired people in communication A sign language helping hearing impaired people in communication is not popular to ordinary healthy people. In this paper, we propose a method for real-time sign language recognition from a vision system using color information and fuzzy clustering system. We use YCbCr color model and canny mask to decide the position of hands and the boundary lines. After extracting regions of two hands by applying 8-directional contour tracking algorithm and morphological information, the system uses FCM in classifying sign language signals. In experiment, the proposed method is proven to be sufficiently efficient.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.319-327
• /
• 2022

Transformers are the most famous deep learning models that has achieved great success in natural language processing and also showed good performance on computer vision. In this survey, we categorized transformer-based models for computer vision, particularly object detection tasks and perform comprehensive comparative experiments to understand the characteristics of each model. Next, we evaluated the models subdivided into standard transformer, with key point attention, and adding attention with coordinates by performance comparison in terms of object detection accuracy and real-time performance. For performance comparison, we used two metrics: frame per second (FPS) and mean average precision (mAP). Finally, we confirmed the trends and relationships related to the detection and real-time performance of objects in several transformer models using various experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.105.2-105
• /
• 2001

This paper studies continuous Korean Sign Language (KSL) recognition using color vision. In recognizing gesture words such as sign language, it is a very difficult to segment a continuous sign into individual sign words since the patterns are very complicated and diverse. To solve this problem, we disassemble the KSL into 18 hand motion classes according to their patterns and represent the sign words as some combination of hand motions. Observing the speed and the change of speed of hand motion and using state automata, we reject unintentional gesture motions such as preparatory motion and meaningless movement between sign words. To recognize 18 hand motion classes we adopt Hidden Markov Model (HMM). Using these methods, we recognize 5 KSL sentences and obtain 94% recognition ratio.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.30-37
• /
• 2011

This paper proposes a language set of hand motions for enhancing the performance of vision-based hand signal recognizer. Based on the statistical analysis of the angular tendency of hand movements in sign language and the hand motions in practical use, we construct four motion primitives as building blocks for basic hand motions. By combining these motion primitives, we design a discernable 'fundamental hand motion set' toward increasing the hand signal recognition. To demonstrate the validity of proposed designing method, we develop a 'fundamental hand motion set' recognizer based on hidden Markov model (HMM). The recognition system showed 99.01% recognition rate on the proposed language set. This result validates that the proposed language set enhances discernaility among the hand motions such that the performance of hand signal recognizer is improved.

• The Journal of Information Systems
• /
• v.25 no.1
• /
• pp.135-158
• /
• 2016

Purpose Virtual communities change the way people communicate and share information. The purpose of this paper is to find how internet social capital and individual motivations influence the information sharing in virtual communities. This study considers the social capital theory, individual motivations, information sharing, and community promotion to construct a theoretical model. Design/methodology/approach Social capital focuses on three dimensions that include 6 factors: social interaction ties, centrality, shared language, shared vision, trust and reciprocity. Individual motivations include 2 factors: reputation and enjoy helping. To confirm the research model and the hypotheses, 426 effective questionnaires were used for the final analysis. Findings The result of data analysis demonstrates that social interaction ties, centrality, shared language, trust, and reciprocity were significant in affecting information sharing behaviors. However, reputation, enjoy helping, and shared vision does not appear to have a significant influence on information sharing behaviors. The information sharing was positively related to community promotion.

• Korean Journal of Radiology
• /
• v.25 no.3
• /
• pp.224-242
• /
• 2024

The emergence of Chat Generative Pre-trained Transformer (ChatGPT), a chatbot developed by OpenAI, has garnered interest in the application of generative artificial intelligence (AI) models in the medical field. This review summarizes different generative AI models and their potential applications in the field of medicine and explores the evolving landscape of Generative Adversarial Networks and diffusion models since the introduction of generative AI models. These models have made valuable contributions to the field of radiology. Furthermore, this review also explores the significance of synthetic data in addressing privacy concerns and augmenting data diversity and quality within the medical domain, in addition to emphasizing the role of inversion in the investigation of generative models and outlining an approach to replicate this process. We provide an overview of Large Language Models, such as GPTs and bidirectional encoder representations (BERTs), that focus on prominent representatives and discuss recent initiatives involving language-vision models in radiology, including innovative large language and vision assistant for biomedicine (LLaVa-Med), to illustrate their practical application. This comprehensive review offers insights into the wide-ranging applications of generative AI models in clinical research and emphasizes their transformative potential.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4625-4647
• /
• 2020

The Generative Adversarial Networks, as one of the most creative deep learning models in recent years, has achieved great success in computer vision and natural language processing. It uses the game theory to generate the best sample in generator and discriminator. Recently, many deep learning models have been applied to the security field. Along with the idea of "generative" and "adversarial", researchers are trying to apply Generative Adversarial Networks to the security field. This paper presents the development of Generative Adversarial Networks. We review traditional generation models and typical Generative Adversarial Networks models, analyze the application of their models in natural language processing and computer vision. To emphasize that Generative Adversarial Networks models are feasible to be used in security, we separately review the contributions that their defenses in information security, cyber security and artificial intelligence security. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

• Journal of Venture Innovation
• /
• v.6 no.1
• /
• pp.161-179
• /
• 2023

More than 2 million foreigners were staying in Korea. In this study, the effect of individual and environmental characteristics of foreign workers on organizational commitment was empirically analyzed. A research model for empirical analysis was established. A research model was established independent variables by dividing them into four parts: personal desire, adaptability, organizational life, and social support and setting organizational commitment as dependent variables. Based on this research model, data collection for analysis was conducted in a survey method for foreign workers in Korea. An empirical analysis was conducted using SPSS 24 based on 200 valid sample of the respondents. The results of the empirical analysis were as follows. First, it was found that foreign workers' desire for achievement, language adaptability, relationships with supervisors and colleagues, future vision of jobs, and social support had a significant positive (+) effect on organizational commitment. On the other hand, the significant influence relationship of cultural adaptability was not tested. Second, factors that significantly affect organizational commitment was in the order of social support, relationships with supervisors and colleagues, future vision of jobs, language adaptability, and desire for achievement. Based on these research results, academic implications were presented, and practical implications were presented to increase the organizational commitment of foreign workers.

• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.35-49
• /
• 2024

Video captioning technology, as a significant outcome of the integration between computer vision and natural language processing, has emerged as a key research direction in the field of artificial intelligence. This technology aims to achieve automatic understanding and language expression of video content, enabling computers to transform visual information in videos into textual form. This paper provides an initial analysis of the research trends in deep learning-based video captioning and categorizes them into four main groups: CNN-RNN-based Model, RNN-RNN-based Model, Multimodal-based Model, and Transformer-based Model, and explain the concept of each video captioning model. The features, pros and cons were discussed. This paper lists commonly used datasets and performance evaluation methods in the video captioning field. The dataset encompasses diverse domains and scenarios, offering extensive resources for the training and validation of video captioning models. The model performance evaluation method mentions major evaluation indicators and provides practical references for researchers to evaluate model performance from various angles. Finally, as future research tasks for video captioning, there are major challenges that need to be continuously improved, such as maintaining temporal consistency and accurate description of dynamic scenes, which increase the complexity in real-world applications, and new tasks that need to be studied are presented such as temporal relationship modeling and multimodal data integration.