ICMR 2023: 12-15 June 2023 Thessaloniki, Greece
ICDAR 2023 (hybrid) – the 4th workshop on Intelligent Cross-Data Analytics and Retrieval
https://www.xdata.nict.jp/icdar_icmr2023/
Data plays a critical role in human life. In the digital era, where data can be collected almost anywhere and anytime, people have access to a vast volume of real-time data that reflects their living environment differently. People can extract necessary information from these data to gain knowledge and become wiser.
Nevertheless, data often comes from multiple sources and only reflects a small part of the big puzzle of life. Despite potentially missing some pieces, the goal is to capture the puzzle's image with the available pieces. The more pieces of data we can collect and assemble within a given frame, the faster we can solve the puzzle. The challenge becomes even more significant when dealing with multimodal data, cross-domain and cross-platform problems. A multimodal data puzzle would be one where pieces have different shapes and sizes. A cross-domain puzzle would be one where the pieces come from distinct sub-pictures. Finally, a cross-platform puzzle would be one where the pieces assembled come from different puzzles. But in all these scenarios, you still have to put the pieces together to get the entire picture. The proposed research topic of “Intelligent Cross-Data Analysis and Retrieval” aims to advance the field of cross-data analytics and retrieval and contribute to developing a more intelligent and sustainable society. This workshop welcomes researchers coming from diverse domains and disciplines, such as well-being, disaster prevention and mitigation, mobility, climate change, tourism, healthcare, and more
The proposed research topic of “Intelligent Cross-Data Analysis and Retrieval” aims to advance the field of cross-data analytics and retrieval and contribute to developing a more intelligent and sustainable society. This workshop welcomes researchers from diverse domains and disciplines, including well-being, disaster prevention and mitigation, mobility, climate change, tourism, healthcare, and more.
Example topics include, but are not limited to:
– Event-based cross-data retrieval Data mining and AI technology.
– Multimodal complex event processing
– Transfer Learning and Transformers.
– Multimodal self-supervised learning
– Heterogeneous data association discovery.
– Cross-datasets for Repeatable Experimentation.
– Federated Analytics and Federated Learning for cross-data.
– Privacy-public data collaboration.
– Diverse multimodal data Integration.
– Realization of a prosperous and independent region in which people and nature coexist.
– Intelligent cross-data analysis applications from different domains
Paper submission:
ü All papers must be formatted according to the ACM proceedings style.
ü All technical content, including the main text, figures, and tables, without references, should be included within the page limit (eight pages for regular papers and four pages for short papers).
ü For any over-length submission, we reserve the right to reject it outright on an administrative basis.
Important Dates:
ü Feb. 28, 2023: Deadline for Paper Submission
ü Mar. 31, 2023: Notification of Acceptance
ü Apr. 20, 2023: Camera-Ready Paper Due
ü (TBD) – Workshops Day
Organizers*
ü Guillaume Habault, KDDI Research Inc., Japan
ü Michael Alexander Riegler, Simula Metropolitan Center for Digital Engineering, Norway
ü Minh-Son Dao, National Institute of Information and Communications Technology (NICT), Japan
ü Duc-Tien Dang-Nguyen, Bergen University, Norway
ü Yuta Nakashima, Osaka University, Japan
ü Cathal Gurrin, Dublin City University, Ireland
Contact:
https://www.xdata.nict.jp/icdar_icmr2023/
https://icmr2023.org/
✉ xgu-habault@kddi.com>
✉ dao@nict.go.jp
February 2nd, 2023
Daniela Lopez de Luise
I am happy to announce the new special issue with IEEE Transaction on Artificial Intelligence (TAI) is live now and welcome submissions. The theme is “Automated Machine Learning for Non-Stationary Data”.
SI website with all the information: http://tai.amlnsd.com
Submission deadline 2nd of June, 2023.
Submission information: https://cis.ieee.org/publications/ieee-transactions-on-artificial-intelligence/information-for-authors-tai
(Please select this special issue in the Manuscript Central System when submitting your paper at Step 1.)
Description: Nowadays, data is commonly collected over time and susceptible to changes. A model trained under a false stationarity assumption is bound to become obsolete in time. It also happens to existing Automated Machine Learning (AutoML) systems. For more flexible and robust AutoML models over time, this special issue will integrate the growing international community of researchers working on AutoML and data stream learning, and have a fruitful collection of high-quality papers on the evolution and future development of AutoML.
Topics of interest (including but not limited to):
(1) AutoML solutions for temporal data and data streams:
l Change detection techniques
l Adaptation strategies in AutoML pipelines
l Online and incremental learning in AutoML
l Meta learning and lifelong learning
l Model evaluation methods
l Dynamic hyperparameter optimization
l Automated construction of configuration space.
(2) Contemporary AutoML:
l Hyperparameter and architecture optimization for non-stationary data
l Multi-objective AutoML
l AutoML fairness, interpretability and robustness
l Transfer learning in AutoML
l Human-in-the-Loop AutoML
l Automated model exploration approaches
l AutoML in distributed learning environments
l Automated class imbalance learning
(3) Applied and cross-disciplinary topics:
l Spatial-temporal modeling for Geoinformatics
l Sensory data analysis
l Computer vision
l Biometric identification and recognition
l Automated software engineering systems
l Healthcare
l Development of opensource adaptive AutoML systems
Editorial team (in alphabetic order): Ran Cheng (Southern University of Science and Technology, China), Hugo Jair Escalante (National Institute of Astrophysics, Optics and Eletronics, Mexico), Jan N van Rijn (Leiden University, Netherlands), Wei-wei Tu (4Paradigm Inc., China), Shuo Wang (University of Birmingham, UK), Yun Yang (Yunnan University, China).
Best wishes,
February 2nd, 2023
Daniela Lopez de Luise
I am happy to announce the new special issue with IEEE Transaction on Artificial Intelligence (TAI) is live now and welcome submissions. The theme is “Automated Machine Learning for Non-Stationary Data”.
SI website with all the information: http://tai.amlnsd.com
Submission deadline 2nd of June, 2023.
Submission information: https://cis.ieee.org/publications/ieee-transactions-on-artificial-intelligence/information-for-authors-tai
(Please select this special issue in the Manuscript Central System when submitting your paper at Step 1.)
Description: Nowadays, data is commonly collected over time and susceptible to changes. A model trained under a false stationarity assumption is bound to become obsolete in time. It also happens to existing Automated Machine Learning (AutoML) systems. For more flexible and robust AutoML models over time, this special issue will integrate the growing international community of researchers working on AutoML and data stream learning, and have a fruitful collection of high-quality papers on the evolution and future development of AutoML.
Topics of interest (including but not limited to):
(1) AutoML solutions for temporal data and data streams:
l Change detection techniques
l Adaptation strategies in AutoML pipelines
l Online and incremental learning in AutoML
l Meta learning and lifelong learning
l Model evaluation methods
l Dynamic hyperparameter optimization
l Automated construction of configuration space.
(2) Contemporary AutoML:
l Hyperparameter and architecture optimization for non-stationary data
l Multi-objective AutoML
l AutoML fairness, interpretability and robustness
l Transfer learning in AutoML
l Human-in-the-Loop AutoML
l Automated model exploration approaches
l AutoML in distributed learning environments
l Automated class imbalance learning
(3) Applied and cross-disciplinary topics:
l Spatial-temporal modeling for Geoinformatics
l Sensory data analysis
l Computer vision
l Biometric identification and recognition
l Automated software engineering systems
l Healthcare
l Development of opensource adaptive AutoML systems
Editorial team (in alphabetic order): Ran Cheng (Southern University of Science and Technology, China), Hugo Jair Escalante (National Institute of Astrophysics, Optics and Eletronics, Mexico), Jan N van Rijn (Leiden University, Netherlands), Wei-wei Tu (4Paradigm Inc., China), Shuo Wang (University of Birmingham, UK), Yun Yang (Yunnan University, China).
Best wishes,
