Jieun Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Jieun Kim has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jieun Lee
Division of Computer Engineering, Hansung University, Seoul, South Korea
4 shared publications - Hanseob Kim
Department of Computer Science and Software Engineering, Korea University, Sejong, Republic of Korea
3 shared publications - Jae-In Hwang
Korea Institute of Science and Technology
3 shared publications - Bin Han
University of Southern California, Los Angeles, USA
2 shared publications - Ghazanfar Ali
University of Science and Technology, South Korea
2 shared publications - Woohee Park2 shared publications
Latest Publications
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Engaged and Affective Virtual Agents: Their Impact on Social Presence, Trustworthiness, and Decision-Making in the Group Discussion
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessEngaged and Affective Virtual Agents: Their Impact on Social Presence, Trustworthiness, and Decision-Making in the Group Discussion
- Open Access
- 6 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1
ASAP: Auto-generating Storyboard and Previz
We present ASAP, a system that uses virtual humans to Automatically generate Storyboards And Pre-visualized scenes from movie scripts. In our ASAP system, virtual humans play the role of actors. To visualize the screenplay scene, our system understands the movie script, which is the text data, and then facilitates the automatic generation of the following virtual human's non-/verbal behavior: (1) co-speech gesture, (2) facial expression, and (3) body movements. First of all, co-speech gestures are created from dialogue paragraphs using a text-to-gesture model trained with 2D videos and 3D motion-captured data. Next, for the facial expressions, we interpret the actors' emotions in the parenthetical paragraphs and then adjust the virtual human's face animation to reflect emotions such as anger and sadness. For body movements, our system extract action entities from action paragraphs (e.g., subject, target, and action) and then combine sets of animations to make animation sequences (e.g., a man's act of sitting on a bed). As soon as possible, ASAP can reduce the amount of time, money, and labor-intensive work that needs to be done in the early stages of filmmaking.
- 6 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessASAP: Auto-generating Storyboard and Previz
We present ASAP, a system that uses virtual humans to Automatically generate Storyboards And Pre-visualized scenes from movie scripts. In our ASAP system, virtual humans play the role of actors. To visualize the screenplay scene, our system understands the movie script, which is the text data, and then facilitates the automatic generation of the following virtual human's non-/verbal behavior: (1) co-speech gesture, (2) facial expression, and (3) body movements. First of all, co-speech gestures are created from dialogue paragraphs using a text-to-gesture model trained with 2D videos and 3D motion-captured data. Next, for the facial expressions, we interpret the actors' emotions in the parenthetical paragraphs and then adjust the virtual human's face animation to reflect emotions such as anger and sadness. For body movements, our system extract action entities from action paragraphs (e.g., subject, target, and action) and then combine sets of animations to make animation sequences (e.g., a man's act of sitting on a bed). As soon as possible, ASAP can reduce the amount of time, money, and labor-intensive work that needs to be done in the early stages of filmmaking.
- Open Access
- 6 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-2
No-code Digital Human for Conversational Behavior
In this poster, we present Flow Human, a no-code system that generates conversational behavior of digital humans from the text. Our users only need to build a conversation flow they want to talk to customers using the flow-based authoring tool we developed. Our system then automatically generates the verbal and non-verbal behavior of digital humans along the conversation flow, interacts with customers, and collects feedback. We believe that this work can serve the potential to be distributed to various services that have not been introduced because of the challenging task of controlling multiple factors in digital humans (e.g., conversation flow, co-speech gestures, and facial animation).
- 6 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessNo-code Digital Human for Conversational Behavior
In this poster, we present Flow Human, a no-code system that generates conversational behavior of digital humans from the text. Our users only need to build a conversation flow they want to talk to customers using the flow-based authoring tool we developed. Our system then automatically generates the verbal and non-verbal behavior of digital humans along the conversation flow, interacts with customers, and collects feedback. We believe that this work can serve the potential to be distributed to various services that have not been introduced because of the challenging task of controlling multiple factors in digital humans (e.g., conversation flow, co-speech gestures, and facial animation).
- Open Access
- 20 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 65809-65824
VR Color Picker: Three-Dimensional Color Selection Interfaces
In this paper, we propose a 3D color picker for virtual reality (VR) systems. Using the proposed color picker, the RGB and HSV color spaces are displayed in 3D shape, and a color can be selected through a one-step interaction by pointing at a location inside the color space with a 3D pointing device. This process is very simple compared with the multistep color selection interactions required for existing VR color pickers. Since the interior of the color space is not visible, we also propose three types of user interfaces that show the interior of the color space. These interfaces either cut out a portion of the color space, show cross-sections of the color space, or show discrete samples placed in the color space. We conducted user experiments on the color selection time, color selection accuracy, and usability and proved the usefulness and effectiveness of the proposed VR color picker.
- 20 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 65809-65824
Open AccessVR Color Picker: Three-Dimensional Color Selection Interfaces
In this paper, we propose a 3D color picker for virtual reality (VR) systems. Using the proposed color picker, the RGB and HSV color spaces are displayed in 3D shape, and a color can be selected through a one-step interaction by pointing at a location inside the color space with a 3D pointing device. This process is very simple compared with the multistep color selection interactions required for existing VR color pickers. Since the interior of the color space is not visible, we also propose three types of user interfaces that show the interior of the color space. These interfaces either cut out a portion of the color space, show cross-sections of the color space, or show discrete samples placed in the color space. We conducted user experiments on the color selection time, color selection accuracy, and usability and proved the usefulness and effectiveness of the proposed VR color picker.
- Open Access
- 1 June 2021
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 27 (2) , 1-11
Performance Analysis of 3D Color Picker in Virtual Reality
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- 1 June 2021
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 27 (2) , 1-11
Open AccessPerformance Analysis of 3D Color Picker in Virtual Reality
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- 30 September 2020
- Published by Applied Linguistics Association of Korea in Korean Journal of Applied Linguistics
- Vol. 36 (3) , 31-53
Effects of Prior Topic Knowledge and English Language Proficiency on EFL Reading Comprehension of Two Types of Expository Text
Prior knowledge has been proven to be a very influential factor in the reading comprehension of expository texts. Among diverse domains of expository texts, the significant role of prior knowledge in the L1 reading comprehension of science texts has been reported. To examine the role of prior topic knowledge in the L2 reading comprehension of expository texts, 77 Korean high school students read two types of expository texts: two science texts (i.e., chemistry and physics) and two non-science texts (i.e., music and history). We also measured the students’ prior topic knowledge, English proficiency, and reading comprehension to investigate the interaction between prior topic knowledge and English proficiency. According to our multiple regression analyses, both science topic knowledge (β = .48) and English proficiency (β = .43) were significant predictors of reading comprehension in the case of science texts. Additionally, science topic knowledge (β = .53) was a stronger predictor of reading comprehension for the situation model questions that intend for the higher level of comprehension than for the textbase questions that intend for the propositional level of comprehension (β = .36) when reading science texts. In the case of the non-science texts, music and history topic knowledge was not a significant predictor because the readers had generally low prior topic knowledge. The reading comprehension of non-science texts was dominantly explained by English proficiency. Interestingly, science topic knowledge was a significant predictor of reading comprehension of the non-science texts in the case of textbase questions, but not situation model questions.
- 30 September 2020
- Published by Applied Linguistics Association of Korea in Korean Journal of Applied Linguistics
- Vol. 36 (3) , 31-53
Effects of Prior Topic Knowledge and English Language Proficiency on EFL Reading Comprehension of Two Types of Expository Text
Prior knowledge has been proven to be a very influential factor in the reading comprehension of expository texts. Among diverse domains of expository texts, the significant role of prior knowledge in the L1 reading comprehension of science texts has been reported. To examine the role of prior topic knowledge in the L2 reading comprehension of expository texts, 77 Korean high school students read two types of expository texts: two science texts (i.e., chemistry and physics) and two non-science texts (i.e., music and history). We also measured the students’ prior topic knowledge, English proficiency, and reading comprehension to investigate the interaction between prior topic knowledge and English proficiency. According to our multiple regression analyses, both science topic knowledge (β = .48) and English proficiency (β = .43) were significant predictors of reading comprehension in the case of science texts. Additionally, science topic knowledge (β = .53) was a stronger predictor of reading comprehension for the situation model questions that intend for the higher level of comprehension than for the textbase questions that intend for the propositional level of comprehension (β = .36) when reading science texts. In the case of the non-science texts, music and history topic knowledge was not a significant predictor because the readers had generally low prior topic knowledge. The reading comprehension of non-science texts was dominantly explained by English proficiency. Interestingly, science topic knowledge was a significant predictor of reading comprehension of the non-science texts in the case of textbase questions, but not situation model questions.
- Open Access
- 1 July 2020
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 26 (3) , 79-86
A Study on the Design and Effect of Feedback for Virtual Reality Exercise Posture Training
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- 1 July 2020
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 26 (3) , 79-86
Open AccessA Study on the Design and Effect of Feedback for Virtual Reality Exercise Posture Training
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- Open Access
- 1 July 2020
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 26 (3) , 69-77
Feedback Design and Analysis for 3-dimensional Drawing in Virtual Reality
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- 1 July 2020
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 26 (3) , 69-77
Open AccessFeedback Design and Analysis for 3-dimensional Drawing in Virtual Reality
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.