IJCAI AffComp 2019: 3rd International Workshop on Artificial Intelligence in Affective Computing Macao, China, August 10, 2019 |
Conference website | http://kdd.cs.ksu.edu/KDD/Workshops/IJCAI-2019-AffComp/ |
Submission link | https://easychair.org/conferences/?conf=ijcaiaffcomp2019 |
Camera ready copy due | July 12, 2019 |
Submission deadline | July 29, 2019 |
Organizing Committee
William H. Hsu (bhsu@ksu.edu)
Google Voice (office/mobile): +1 785 236 8247
Department of Computer Science
2184 Engineering Hall, Kansas State University
1701D Platt Street, Manhattan, KS 66506
Google Scholar: http://bit.ly/2mlZheB
Webpage: http://www.kddresearch.org/
Jennifer Healey (jennifer.healey@intel.com)
Senior Research Scientist, Intel Corporation
2200 Mission College Boulevard
Santa Clara, California 95054-1549
Google Scholar:
Webpage (LinkedIn): http://bit.ly/2CW3Oh9 Nathan Hodas (nathan.hodas@pnnl.gov)
Office: +1 509 375-2862
Pacific Northwest National Lab (PNNL)
902 Battelle Boulevard, Richland, WA 99352
Google Scholar: http://bit.ly/2FmFcMS
Webpage (LinkedIn): http://bit.ly/2AKQZBt
Brent Chamberlain (brentchamberlain@ksu.edu)
Office: +1 785 532 2431
Landscape Architecture and Regional & Community Planning
1153 Seaton Hall, Kansas State University
Manhattan KS, 66506
Google Scholar: http://bit.ly/2qQfIEI
Webpage: http://brentchamberlain.org/
Heath Yates (hlyates@bri.ksu.edu)
Biosecurity Research Institute
Kansas State University
1041 Pat Roberts Hall, Manhattan KS 66506
Google Scholar: http://bit.ly/2Desu2p
Webpage: http://bit.ly/2qN0U9R
Nathan Hodas
Senior Research Scientist
Pacific Northwest National Laboratory
Google Scholar: http://bit.ly/31pgkzh
Ognjen Rudovic
Research Fellow
MIT Media Lab
Google Scholar: http://bit.ly/2XE6k2T
Technical Description of Workshop
In recent years, interest in affective computing (AC) have led to advances in speech recognition, natural language processing, facial expression detection, and applying machine learning using wearables. The workshop will focus on the convergence of methodologies that contribute to detecting emotional and psychometric patterns based on machine learning algorithms, wearables, Internet of Things (IoT), and databases to capture important aspects of affective computing.
Active research areas that are relevant to affective computing include:
• Health centric applications using affective computing to enhance healthcare
• Multimodal sensor fusion to comprehensively detect and classify affect in users
• User environments for the design of systems to better detect and classify affect
• Applications using wearables to detect/classify affect, stress, fatigue, and medical emergencies
• Recognition/prediction of affect and emotion using artificial neural networks and/or deep learning
• Social informatics applications: group behavioral effects and feedback, location-awareness
• Predicting/classifying real-time annotated data using spatiotemporal learning and inference
• Machine learning using biometric data to classify biosignals
• Wearable computing applications, especially based on experience sampling methods
• Facial recognition in predicting bonding in conversations
• Electrothermal methodologies in affective computing
• Understanding Emotions in Context: Home vs. work, friends vs. strangers, online vs. in person, conversations, while driving, and etc
The emphasis of this workshop shall be approaches based on the extraction of emotional and physiometric patterns from heterogeneous sources including but not limited to wearables, spatiotemporal methods, artificial neural networks, deep learning, and other machine learning and inference algorithms.
Application areas that exhibit extant needs for affective computing include:
• Biomedical Research: medical informatics, behavioral and cognitive neuroscience
• Environments: ubiquitous computing, mobile computing, user experience design
• Data Science for Social Good: computational sustainability, disaster management
• Wearable Computing: health applications, sensor analytics, mobile applications
• Internet of Things (IoT) and Cyber-Physical Systems: spatiotemporal, hybrid systems
• Human Computer Interaction (HCI): augmented reality/mixed reality systems, usability
• Other Application Areas: mobile computing, virtual reality
This workshop shall help to bring together people from these different areas and present an opportunity for researchers and practitioners to share new techniques for identifying and analyzing applications in affective computing that integrate multiple fields and disciplines. We also propose to coordinate with the wearables community to find opportunities for cross-fertilization and interdisciplinary collaboration.
Intended Audience and Impact
The intended audience shall consist of artificial intelligence researchers from core areas such as statistical methodologies, machine learning, pattern recognition, probabilistic reasoning, ontologies and learning representation, as well as transdisciplinary and multidisciplinary domains such as data science, spatiotemporal analytics of affect, data modeling and mining, cyber-physical systems (CPS) and hybrid systems including wearable computing and IoT analytics, and virtual reality (VR) / augmented reality (AR) / mixed reality systems. Benefits will thus accrue to the data science of affective computing and to advances in CPS/IoT, VR/AR, and smart environments. The workshop will also be of interest to researchers and practitioners of application areas, such as: Smart environments including homes, offices, and schools; assistive technologies, especially for children, the elderly, and the disabled; and medical and social uses of affect recognition.
Workshop Logistics
The workshop will be a single-day event featuring morning and afternoon technical sessions. In the spirit of fostering new research and collaboration, care will be taken to maximize available time for discussions and questions. The program committee will aim at accepting about 8-10 technical papers for full oral presentation.
Following brief welcoming remarks, a 3-hour morning session will consist of approximately half the oral technical presentations. A single invited talk following the lunch break will be aimed at serving the interests of a variety of intelligent systems researchers and attracting new researchers to the topic of heterogeneous information networks. The afternoon session will include the second half of the technical papers, concluding early with an optional poster session and a brief open discussion about possible special issues of journals on the topic. The goal of both concluding sessions is to provide additional opportunities for cross-fertilization between academic and industrial research, through introduction of applications and methodologies that may otherwise be unfamiliar to participants in diverse areas.
Relevant Past Workshops
Recent Events Related to Proposed Topic (next 2 year and last 2 years, reverse chronological order)
ACII 2019, TBD
ICACII 2018, 26 Mar – 27 Mar
AAAI 2018, 2 Feb – 7 Feb
ACII 2017, 23 Oct – 26 Oct
IJCAI AffComp – 1st workshop 2017, 19 Aug – 25 Aug
ASC 2017, 13 Feb – 17 Feb
HMII 2016, 22 Nov – 25 Nov
ERM4CT 2016, 16 Nov
Accepted IJCAI AffComp 1st Workshop 2017 Publications
Liu, D., Fengjiao, P., Rudovic, O.(. & Picard, R.. (2017). DeepFaceLIFT: Interpretable Personalized Models for Automatic Estimation of Self-Reported Pain. Proceedings of IJCAI 2017 Workshop on Artificial Intelligence in Affective Computing, in PMLR 66:1-16
Jaques, N., Rudovic, O.(., Taylor, S., Sano, A. & Picard, R.. (2017). Predicting Tomorrow’s Mood, Health, and Stress Level using Personalized Multitask Learning and Domain Adaptation. Proceedings of IJCAI 2017 Workshop on Artificial Intelligence in Affective Computing, in PMLR 66:17-33
Atcheson, M., Sethu, V. & Epps, J.. (2017). Gaussian Process Regression for Continuous Emotion Recognition with Global Temporal Invariance. Proceedings of IJCAI 2017 Workshop on Artificial Intelligence in Affective Computing, in PMLR 66:34-44
Li, M., Lu, Q., Long, Y. & Gui, L.. (2017). Affective State Prediction of Contextualized Concepts. Proceedings of IJCAI 2017 Workshop on Artificial Intelligence in Affective Computing, in PMLR 66:45-57
Yates, H., Chamberlain, B., Norman, G. & Hsu, W.H.. (2017). Arousal Detection for Biometric Data in Built Environments using Machine Learning. Proceedings of IJCAI 2017 Workshop on Artificial Intelligence in Affective Computing, in PMLR 66:58-72
Program Committee
Erik Cambria, Nanyang Technological University (Singapore)
Asma Ghandeharioun, Massachusetts Institute of Technology (USA)
Natasha Jaques, Massachusetts Institute of Technology (USA)
Leimin Tian, University of Edinburgh (UK)
Sara Taylor, Massachusetts Institute of Technology (USA)
Yuqian Zhou, University of Illinois at Urbana-Champaign (USA)