Publications
Proceedings, refereed
A Comparative Study of Interactive Environments for Investigative Interview of A Virtual Child Avatar
In IEEE international symposium on multimedia (ISM). IEEE, 2022.Status: Published
A Comparative Study of Interactive Environments for Investigative Interview of A Virtual Child Avatar
Afilliation | Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | IEEE international symposium on multimedia (ISM) |
Pagination | 194-201 |
Publisher | IEEE |
DOI | 10.1109/ISM55400.2022.00043 |
Comparison of Crowdsourced and Remote Subjective User Studies: A Case Study of Investigative Child Interviews
In The 14th International Conference on Quality of Multimedia Experience. IEEE, 2022.Status: Published
Comparison of Crowdsourced and Remote Subjective User Studies: A Case Study of Investigative Child Interviews
Afilliation | Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | The 14th International Conference on Quality of Multimedia Experience |
Publisher | IEEE |
URL | https://ieeexplore.ieee.org/document/9900900 |
DOI | 10.1109/QoMEX55416.2022.9900900 |
Investigative Interviews using a Multimodal Virtual Avatar
In American Psychology-Law Society Conference 2022. Denver USA,: American Psychology-Law Society, 2022.Status: Accepted
Investigative Interviews using a Multimodal Virtual Avatar
To meet best-practice standards, we are developing an interactive virtual avatar aiming as a training tool to raise interviewing skills of child-welfare and law-enforcement professionals. Therefore, we present the “Ilma” avatar that recognizes interviewers’ behavior during open-ended, closed and leading questions, and which can automatically respond to the conversation. We conducted a user study in which master students (N=3) and child protective workers (N=8) interviewed “Ilma” and rated their perception of the interaction. The results show that the participants valued the interaction and found the avatar useful. Thus, it has great potential to be an effective training tool.
Afilliation | Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | American Psychology-Law Society Conference 2022 |
Publisher | American Psychology-Law Society |
Place Published | Denver USA, |
Is More Realistic Better? A Comparison of Game Engine and GAN-based Avatars for Investigative Interviews of Children
In ICDAR '22: Proceedings of the 3rd ACM Workshop on Intelligent Cross-Data Analysis and Retrieval. New York, NY, USA: ACM, 2022.Status: Published
Is More Realistic Better? A Comparison of Game Engine and GAN-based Avatars for Investigative Interviews of Children
Afilliation | Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | ICDAR '22: Proceedings of the 3rd ACM Workshop on Intelligent Cross-Data Analysis and Retrieval |
Pagination | 41-49 |
Publisher | ACM |
Place Published | New York, NY, USA |
ISBN Number | 9781450392419 |
URL | https://dl.acm.org/doi/proceedings/10.1145/3512731 |
DOI | 10.1145/351273110.1145/3512731.3534209 |
Towards an AI-driven talking avatar in virtual reality for investigative interviews of children
In GameSys '22: Proceedings of the 2nd Workshop on Games Systems. New York, NY, USA: ACM, 2022.Status: Published
Towards an AI-driven talking avatar in virtual reality for investigative interviews of children
Afilliation | Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | GameSys '22: Proceedings of the 2nd Workshop on Games Systems |
Pagination | 9-15 |
Publisher | ACM |
Place Published | New York, NY, USA |
ISBN Number | 9781450393812 |
URL | https://dl.acm.org/doi/10.1145/3534085.3534340 |
DOI | 10.1145/353408510.1145/3534085.3534340 |
Virtual Reality Talking Avatar for Investigative Interviews of Maltreat Children
In 19th International Conference on Content-based Multimedia Indexing. New York, NY, USA: Association for Computing Machinery (ACM), 2022.Status: Published
Virtual Reality Talking Avatar for Investigative Interviews of Maltreat Children
Afilliation | Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | 19th International Conference on Content-based Multimedia Indexing |
Pagination | 201-204 |
Publisher | Association for Computing Machinery (ACM) |
Place Published | New York, NY, USA |
ISBN Number | 9781450397209 |
URL | https://doi.org/10.1145/3549555.3549572 |
DOI | 10.1145/3549555.3549572 |
Journal Article
SinGAN-Seg: Synthetic training data generation for medical image segmentation
PLOS ONE 17, no. 5 (2022): e0267976.Status: Published
SinGAN-Seg: Synthetic training data generation for medical image segmentation
Analyzing medical data to find abnormalities is a time-consuming and costly task, particularly for rare abnormalities, requiring tremendous efforts from medical experts. Therefore, artificial intelligence has become a popular tool for the automatic processing of medical data, acting as a supportive tool for doctors. However, the machine learning models used to build these tools are highly dependent on the data used to train them. Large amounts of data can be difficult to obtain in medicine due to privacy reasons, expensive and time-consuming annotations, and a general lack of data samples for infrequent lesions. In this study, we present a novel synthetic data generation pipeline, called SinGAN-Seg, to produce synthetic medical images with corresponding masks using a single training image. Our method is different from the traditional generative adversarial networks (GANs) because our model needs only a single image and the corresponding ground truth to train. We also show that the synthetic data generation pipeline can be used to produce alternative artificial segmentation datasets with corresponding ground truth masks when real datasets are not allowed to share. The pipeline is evaluated using qualitative and quantitative comparisons between real data and synthetic data to show that the style transfer technique used in our pipeline significantly improves the quality of the generated data and our method is better than other state-of-the-art GANs to prepare synthetic images when the size of training datasets are limited. By training UNet++ using both real data and the synthetic data generated from the SinGAN-Seg pipeline, we show that the models trained on synthetic data have very close performances to those trained on real data when both datasets have a considerable amount of training data. In contrast, we show that synthetic data generated from the SinGAN-Seg pipeline improves the performance of segmentation models when training datasets do not have a considerable amount of data. All experiments were performed using an open dataset and the code is publicly available on GitHub.
Afilliation | Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Journal Article |
Year of Publication | 2022 |
Journal | PLOS ONE |
Volume | 17 |
Issue | 5 |
Pagination | e0267976 |
Date Published | 05/2022 |
Publisher | PLOS |
URL | https://doi.org/10.1371/journal.pone.0267976 |
DOI | 10.1371/journal.pone.0267976 |
Synthesizing a Talking Child Avatar to Train Interviewers Working with Maltreated Children
Big Data and Cognitive Computing 6, no. 2 (2022): 62.Status: Published
Synthesizing a Talking Child Avatar to Train Interviewers Working with Maltreated Children
Afilliation | Communication Systems, Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Journal Article |
Year of Publication | 2022 |
Journal | Big Data and Cognitive Computing |
Volume | 6 |
Issue | 2 |
Pagination | 62 |
Date Published | Jan-06-2022 |
Publisher | MDPI |
URL | https://www.mdpi.com/2504-2289/6/2/62https://www.mdpi.com/2504-2289/6/2/... |
DOI | 10.3390/bdcc6020062 |
Proceedings, refereed
Multimodal Virtual Avatars for Investigative Interviews with Children
In Proceedings of the 2021 Workshop on Intelligent Cross-Data Analysis and Retrieval (ICDAR '21). New York, NY, USA: ACM, 2021.Status: Published
Multimodal Virtual Avatars for Investigative Interviews with Children
In this article, we present our ongoing work in the field of training police officers who conduct interviews with abused children. The objectives in this context are to protect vulnerable children from abuse, facilitate prosecution of offenders, and ensure that innocent adults are not accused of criminal acts. There is therefore a need for more data that can be used for improved interviewer training to equip police with the skills to conduct high-quality interviews. To support this important task, we propose to research a training program that utilizes different system components and multimodal data from the field of artificial intelligence such as chatbots, generation of visual content, text-to-speech, and speech-to-text. This program will be able to generate an almost unlimited amount of interview and also training data. The goal of combining all these different technologies and datatypes is to create an immersive and interactive child avatar that responds in a realistic way, to help to support the training of police interviewers, but can also produce synthetic data of interview situations that can be used to solve different problems in the same domain.
Afilliation | Communication Systems, Machine Learning |
Project(s) | Department of Holistic Systems |
Publication Type | Proceedings, refereed |
Year of Publication | 2021 |
Conference Name | Proceedings of the 2021 Workshop on Intelligent Cross-Data Analysis and Retrieval (ICDAR '21) |
Publisher | ACM |
Place Published | New York, NY, USA |
ISBN Number | 9781450385299 |
URL | https://dl.acm.org/doi/proceedings/10.1145/3463944 |
DOI | 10.1145/346394410.1145/3463944.3469269 |