The
ICIC 2025 Program Committee is inviting proposals for special
sessions to be held during the conference(http://www.ic-icc.cn/2025/index.htm),
taking place on July 26-29, 2025, in Ningbo, China.
Each
special session proposal should be well motivated and should consist
of 8 to 12 papers. Each paper must have the title, authors with
e-mails/web sites, and as detailed an abstract as possible. The
special session organizer(s) contact information should also be
included. All special session organizers must obtain firm
commitments from their special session presenters and authors to
submit papers in a timely fashion (if the special session is
accepted) and, particularly, present them at the ICIC 2025. Each
special session organizer will be session chair for their own
special sessions at ICIC 2025 accordingly. All planned papers for
special sessions will undergo the same review process as the ones in
regular sessions. All accepted papers for special sessions will also
be published by Springer's Lecture Notes in Computer Sciences
(LNCS)/ Lecture Notes in Artificial Intelligence (LNAI)/ Lecture
Notes in Bioinformatics (LNBI).
All
the authors for each special session must follow the guidelines in CALL
FOR PAPERS to
prepare your submitted papers.
Proposals
for special sessions should be submitted in ELECTRONIC
FORMAT
by http://www.ic-icc.cn/icg/index.php
at Special Session.
|
orders |
Title |
Organizers |
Nationality |
|
The
6th International Session on Theoretical Computational
Intelligence and Applications in 2025 |
Wenzheng
Bao |
China |
|
|
Advancements
in Multimodal Intelligent Computing |
Yong
Su |
China |
|
|
Computational
Intelligence Models for Smart Cities |
Pengjiang
Qian
Khin-Wee
Lai |
China |
|
|
A
Contrastive Learning Framework for Alzheimer's Disease
Classification CLFAD |
Peiyuan
Li
Jiangnan
University |
China |
|
|
Test-Time
Training: Methods, Theory, and Applications |
Lingjie
Li |
China |
1. The
6th International Session on Theoretical Computational
Intelligence and Applications in 2025
Organizer:
Wenzheng Bao
Xuzhou University of Technology
Email: baowz55555@126.com
Scope and Topics:
Since the birth of
artificial intelligence, the theory and technology are increasingly
mature. The application field is also expanding. According to some
laws and mechanisms in the process of natural evolution, and
researchers deal with problems though imitation. That is where
theoretical computational intelligence comes in. Theoretical
computational intelligence is the successor of artificial
intelligence. In addition, it turns into one of the most active
researches in the field of intelligent information science.
Theoretical computational intelligence has been successfully used to
solve the critical problems in pattern recognition, data mining,
image processing and so on. Nowadays, there is some representative
algorithms in the field such as fuzzy systems, neural networks,
evolutionary computation, group intelligence and immune system, etc.
Recently, theoretical computational intelligence is at rapid
development, in the case of both methodological development and
practical applications. Computational intelligence plays pivotal
roles in finding the stable convergence of the optimal solution or
approximate optimal solution through multiple iterative calculation.
Especially in practical applications, it has been widely implemented
by researchers. Computational intelligence is an essential
combination of learning, adaptation and evolution used to
intelligent and innovative applications. Similar to other scientific
domains, there is no doubt that computational intelligence has a
great research space both in theory and in applications. This
workshop consists of invited talks and contributed talks, and
welcomes submission of both papers and short abstracts, where all
submissions will be subject to peer review. The topics of interest
include but are not limited to the following: Applications of
theoretical Computational Intelligence in bioinformatics
Applications of theoretical Computational Intelligence in traffics
Applications of theoretical Computational Intelligence in
pharmaceutics Applications of theoretical Computational Intelligence
in pharmacology Applications of theoretical Computational
Intelligence in Computational chemistry Applications of theoretical
Computational Intelligence in Microbiomics Applications of
theoretical Computational Intelligence in image processing
Applications of theoretical Computational Intelligence in natural
language processing Applications of theoretical Computational
Intelligence in financial Other related topics.
2.
Advancements in Multimodal Intelligent Computing
Organizers:
Yong Su
Tianjin Normal University
Email: suyong@tju.edu.cn
Meng Xing
Ningbo Institute of Digital Twin
Email:
xingmeng@tju.edu.cn
Yijun Yang
The Chinese University of Hong Kong
Email: yjyang@cse.cuhk.edu.hk
Long Tian
Southwest Jiaotong University
Email: long.tian@swjtu.edu.cn
Wei Shang
City University of Hong Kong
Email: csweishang@gmail.com
Scope and Topics:
With the rapid
development of information technology, multimodal data processing
has become a core research direction in the field of artificial
intelligence. Multimodal data originates from various sensory
channels or devices, including images, text, speech, and sensor
data. Each modality provides a different perspective or
understanding of the same phenomenon or object, contributing to a
richer and more comprehensive representation. Efficiently
integrating and processing these heterogeneous datasources to
enhance the perceptual, reasoning, and decision making capabilities
of intelligent systems has become a key challenge across multiple
research domains. This special session aims to comprehensively
explore the latest advancements, technical challenges, and practical
applications of multimodal data processing. Themes of interest：
The special session welcomes research contributions related to the
following topics: 1. Cross-modal feature extraction, alignment, and
representation learning 2. Design and optimization of multimodal
data fusion models 3. Applications for healthcare 4. Applications
for intelligent systems 5. Social media and information retrieval 6.
Smart cities and environmental monitoring 7. Evaluation and dataset
construction 8. Autonomous systems and robotics 9.Human-computer
interaction and user experience 10. Security, privacy, and ethical
considerations in multimodal system.
3.
Computational Intelligence
Models for Smart Cities
Organizers:
Pengjiang Qian
iangnan
University, China
Email: qianpjiang@jiangnan.edu.cn
Wenbing Zhao
Cleveland
State University, USA
Email:
wenbing@ieee.org
Khin-Wee Lai
University
of Malaya, Malaysia
Email:
lai.khinwee@um.edu.my
Scope and Topics:
Smart city comprehensive
adopts the new generation of Internet, big data, Internet of Things,
artificial intelligence, cloud computing and other information
technologies to realize the intelligence of urban construction,
planning, management, and service, forming an innovative and
sustainable intelligent city. It integrates a variety of new
generation information technologies to complete the automatic
perception, collection, integration, analysis and sharing of urban
information resources, and realize intelligent medical care,
emergency response, environmental protection, education,
transportation, etc., thus bringing convenience, high-efficiency,
intelligence to people's life and response to their personalized
needs. The construction of smart city involves many aspects, from
urban road traffic to urban spatial layout and management, which
require high technical support, as well as a complete
information-based decision-making mechanism to provide a reliable
guarantee for urban development. In recent years, advanced
computational intelligence models such as deep learning, active
learning, transfer learning and information fusion have brought
opportunities for smart city. Computational intelligence models have
been successfully applied in many areas of smart city construction,
such as urban traffic flow prediction, health monitoring and early
warning, mobile intelligent question answering system, intelligent
environmental resource deployment, etc. Although the existing
computational intelligence models based on single-view data have
achieved certain results, their practical application performance
still cannot meet the needs of smart city construction. Compared
with single-view data, multi-view data can provide more abundant and
comprehensive information for the computational intelligence models,
thereby further improving the performance of the model. Therefore,
it is necessary to study the deep multi-view learning-driven
computational intelligence model to overcome the defects existing in
the construction of smart cities. In this special issue, we hope to
build a platform for researchers and engineers to explore this field
and contribute their experience and wisdom to the development of
computational intelligence models for smart cities. Topics of
intended papers contain, but not limited to, Advanced computational
intelligence models for smart city, such as deep learning, sparse
learning, transfer learning, active learning, multi-task learning,
Smart city information management platform involving artificial
intelligence, Smart city information decision-making system based on
multi-view data, Prediction models combined with multi-view
features, such as intelligent traffic flow prediction, intelligent
medical disease prediction, intelligent weather prediction, signal
light warning, Visualized human-computer interaction platform for
smart city, Smart city monitoring system driven by deep multi-view
learning, Deployment and management for smart cities with
unsupervised methods, such as self-training models, clustering
algorithms, principal component analysis, Data automated management
and analysis for smart city, Screening and fusion of multi-modal
heterogeneous clinical data for smart medical care with supervision
methods, such as random forest, decision tree, naive bayes, Design
of smart city resource allocation system based on big data analysis
4. A Contrastive Learning Framework
for Alzheimer's Disease Classification CLFAD
Organizers:
Peiyuan Li
Jiangnan University
Email: 6223115015@stu.jiangnan.edu.cn
Zhuxin Peng
Jiangnan University
Email: 6233110032@stu.jiangnan.edu.cn
Qianyi Zhan
Jiangnan University
Email: zhanqianyi@jiangnan.edu.cn
Zhenping Xie
Jiangnan University
Email: xiezp@jiangnan.edu.cn
Yuan Liu
Jiangnan University
Email: lyuan1800@jiangnan.edu.cn
Scope and Topics:
Contrastive
learning,Alzheimer’s
disease, Image Classification, Data augmentation
5.
Test-Time Training:
Methods, Theory, and Applications
Organizers:
Xueliang Li
National Engineering Laboratory for Big Data
System Computing Technology Shenzhen University
Email: lixueliang01@gmial.com
Lingjie Li
College of Big Data and Internet, Shenzhen
Technology University
Email: lilingjie@sztu.edu.cn
Junkai Ji
National Engineering Laboratory for Big Data
System Computing Technology Shenzhen University
Email: jijunkai@szu.edu.cn
Scope and Topics:
Test-Time Training TTT has emerged
as a paradigm to enhance model adaptability and robustness by
allowing continuous learning directly from test data. Unlike
traditional static training, TTT enables models to dynamically
update their parameters or representations during inference,
addressing challenges such as concept drift, domain shifts, and data
scarcity. This approach leverages self-supervised learning,
meta-learning, or online optimization to refine predictions
on-the-fly, making it highly relevant for real-world applications
like autonomous systems, healthcare monitoring, and dynamic
environments. Recent advances in TTT have shown promising results in
improving generalization, reducing catastrophic forgetting, and
enabling lifelong learning. However, key challenges remain,
including theoretical guarantees for stability, efficient
optimization algorithms for real-time adaptation, and scalable
implementations across heterogeneous platforms. This session aims to
foster discussions on cutting-edge TTT methodologies, their
theoretical foundations, and interdisciplinary applications. More
details can be found via http: http://www.ic-icc.cn/2025/index.php.
Topics include but are not restricted to : Theory of Test-Time
Training in Dynamic Environments Optimization Algorithms for
Test-Time Training Self-Supervised Learning for Test-Time Training
Transfer Learning for Test-Time Training Meta-Learning Frameworks
for Test-Time Training Benchmarking and Evaluation Metrics for
Test-Time Training Lifelong Learning Systems for Test-Time Training
Applications of Test-Time Training in Healthcare Monitoring
Applications of Test-Time Training in Computer Vision Applications
of Test-Time Training in Drug Design Applications of Test-Time
Training in Financial Risk Detection