Special Session
Special Session Ⅰ: Multimodal Perception and Its Applications
Session Chair: Prof. Changxin Gao——Huazhong University of Science and Technology, China
Assoc. Prof. Yuanjie Shao——Huazhong University of Science and Technology, China
Information: Nowadays, Multimodal Perception has emerged as a crucial research area in the field of artificial intelligence. By integrating information from multiple sensory modalities such as visual, auditory, and text data, it enables more accurate and comprehensive understanding of the real - world environment. This special session aims to explore the latest advancements in Multimodal Perception technologies and their wide - ranging application scenarios. Multimodal Perception is not only revolutionizing traditional computer vision and audio processing tasks but also finding applications in emerging fields like virtual reality, robotics, and smart healthcare.
The topics to be covered include, but are not limited to:
Multimodal Fusion
Multimodal Object Recognition
Multimodal Scene Understanding
Multimodal Object Detection
Multimodal Learning Algorithms
Multimodal Alignment
Multimodal Retrieval
Multimodal - guided Image Enhancement
Collaborative Perception
Submission Deadline: June 10, 2025
Special Session Ⅱ: Cross-media Intelligent Analysis and Reasoning
Session Chair: Prof. Libo Liu——Ningxia University, China
Dr. Ruonan Zhang——Ningxia University, China
Keywords: Multi-modal/cross-modal Retrieval, Large model, Representation learning, Labeling and description, Interaction, Alignment, Generation, Analysis
Information: The rapid development of internet and multimedia technologies has led to an explosive growth of massive multimodal data (such as images, videos, text, audio, etc.). Efficiently and accurately retrieving user-needed information from these heterogeneous data has become a critical challenge in the field of information retrieval. In this context, Cross-media Intelligent Analysis and Reasoning has emerged, aiming to break down the barriers between different modalities and achieve deep integration of cross-modal semantic understanding and information retrieval.This session will focus on the core technologies, application scenarios, and future development trends of preprocessing in cross-media intelligent analysis to advance the innovation and application of cross-media intelligent analysis and reasoning technologies.
The topics to be covered include, but are not limited to:
Cross-media Representation Learning
Cross-media Knowledge Graph
Cross-media Reasoning Models
Cross-media Retrieval
Cross-media Generation
Cross-media Sentiment Analysis
Cross-media Event Analysis
Applications of Cross-media in Smart Cities, Healthcare, Education, Finance, Entertainment, etc.
Inference, enhancement, and related applications of large models, etc.
Submission Deadline: May 15, 2025
Special Session Ⅲ: Evolutionary Computation and Swarm Intelligence for Solving Dynamic / Large-Scale / Multi-Objective Optimization Problems
Session Chair: Prof. Wei Song——Jiangnan University, China
Keywords: Evolutionary Computation, Swarm Intelligence, Dynamics, Large-scale, Multi-Objective, Optimization
Information: The field of optimization is experiencing a significant transformation driven by advances in computational techniques and artificial intelligence (AI). Dynamic / large-scale / multi-objective optimization （D/L/MO） algorithms attempt to handle complex optimization problems with multi-objectives and/or large-scale decision variables in a changing environment. This session will provide an in-depth understanding of D/L/MO and corresponding diverse applications. We will:
*Solving D/L/MO Problems: Understanding D/L/MO knowledge, principles, capabilities, and emerging techniques for solving D/L/MO problems.
*Exploring Real-World Applications: Learn how D/L/MO algorithms are applied in various scenes such as engineering, logistics, finance, healthcare, etc.
*Seeking Challenges and Opportunities: Finding challenges of existing D/L/MO algorithms, such as reducing computational complexity, accelerating convergence, and preventing premature convergence. Exploring the opportunities that efficient D/L/MO algorithms present in handling real-world problems.
This session is designed for researchers, practitioners, and students interested in D/L/MO. Whether you are an expert or new in the field of D/L/MO, this session will provide valuable insights and foster discussions on how D/L/MO algorithms can address complex optimization problems.
The topics to be covered include, but are not limited to:
Novel algorithms for solving D/L/MO problems, including evolutionary computation, swarm intelligence, reinforcement learning, transfer learning, etc
Hybrid algorithms combining evolutionary computation with other optimization algorithms or learning techniques
Tailored algorithms for solving specific types of D/L/MO problems, e.g., sparse problems, constrained problems, expensive problems, multimodal problems, and others
Applications of existing algorithms to D/L/MO problems in emerging areas, e.g., machine learning, data mining, manufacturing, scheduling, electrics, economics, bioinformatics, medicine, and others
Performance assessment, theoretical analysis, and benchmarking of algorithms for D/L/MO problems
Future directions in D/L/MO: Emerging trends, future research directions, and potential breakthroughs in D/L/MO
Submission Deadline: June 10, 2025
Special Session Ⅳ: Multirobot Collaboration and Its Applications
Session Chair: Assoc. Prof. Jiyu Cheng——Shandong University, China
Keywords: Multirobot System, Collaborative Perception, Collaborative Decision-making, Autonomous Learning
Information: In recent years, as multi-robot systems have been increasingly utilized in various fields such as power inspection, autonomous unmanned vehicle fleets, intelligent warehousing, and logistics, multi-robot technology has gradually become a research hotspot in the field of robotics. In many complex application scenarios, multiple robots cannot pre-acquire environmental map information and need to operate in unknown environments. In such application scenarios, multirobot collaboration becomes particularly important. Therefore, it makes great sense to devote more efforts exploring its potential and shine lights on its future developing direction.
The topics to be covered include, but are not limited to:
Multirobot Exploration and Navigation Algorithms
Machine Learning and Artificial Intelligence in Multirobot Systems
Sensor Fusion and Perception for Multirobot Systems
Multirobot Systems and Heterogeneous Robot Teams
Applications of Autonomous Robot Systems and Swarm Intelligence
Submission Deadline: June 10, 2025
Special Session Ⅴ: Advances in Image Computing
Session Chair: Assoc. Prof. Huanjie Tao——Northwestern Polytechnical University, China
Keywords: Image Classification, Image Recognition, Image captioning, Image Segmentation, Image Reconstruction
Information: Image Computing refers to the technology that utilizes computer to process, analyze, and understand image data, aiming to extract meaningful information, achieve specific functions, or solve practical problems. With the development of deep learning and large models, image computing technologies have made significant progress. This session highlights advances and applications in image computing research.
The topics to be covered include, but are not limited to:
Image classification
Image retrieval
Image registration
Image segmentation
Image captioning
Image watermarking
Image compression
Image generation
Image reconstruction
Image enhancement
Image denoising
Image super-resolution
Image restoration
Image object detection
Image anomaly detection
Image quality assessment
Image depth estimation
Image feature extraction
Image feature learning
Image privacy protection
Image dataset generation
Image computing systems
Image feature representation: Image-level feature representation, dataset-level feature representation
Image-to-text visual question answering
Image dataset quality assessment
Multimodal image fusion
Multi-view image reconstruction
Lightweight image computing models
Medical image processing
Remote sensing image processing
Security and ethical issues in image computing
Large model-based image computing methods
Large-scale image dataset distillation
Traditional image processing methods
Applications of image computing
Submission Deadline: June 15, 2025
Special Session Ⅵ: Mobile Visual Computing
Session Chair: Assoc. Prof. Lingyan Ran——Northwestern Polytechnical University, China
Assoc. Prof. Shizhou Zhang——Northwestern Polytechnical University, China
Keywords: Visual Perception based on Edge Computing, Scene Understanding, Embodied Visioning, Multimodal Sensor Fusion, Multi-modality Cognition
Information: Mobile visual computing refers to the integration of advanced computer vision, image processing, and machine learning technologies into mobile devices (e.g., smartphones, drones, AR/VR headsets) to enable real-time analysis, interpretation, and interaction with visual data. It combines hardware advancements (e.g., high-resolution cameras, GPUs, AI accelerators) with software algorithms to support applications like augmented reality, object recognition, scene reconstruction, and immersive media experiences. Key challenges include optimizing computational efficiency for resource-constrained environments, ensuring low latency, and balancing power consumption. This issue drives innovations in areas such as autonomous navigation, healthcare imaging, and interactive entertainment, reshaping how users perceive and interact with the digital-physical world.
The topics to be covered include, but are not limited to:
Edge-Accelerated Model Compression
Multimodal Sensing and Fusion
Generative AI for Mobile Visual Computing
Energy-Efficient Design for Mobile Visual Systems
Dynamic Environment Adaptation
Submission Deadline: June 15, 2025
Special Session Ⅶ: Intelligent Optimization for Solving Real-Time Constraints and Unsteady Problems in Dynamic System / Large-Scale Scenarios
Session Chair: Prof. Rong Fei——Northwestern Polytechnical University, China
Keywords: Large-Scale Network, Dynamic Optimization, Fault Diagnosis, Data Augmentation, Deep Learning, Performance Evaluation
Information: This special session focuses on the innovation and application of intelligent optimization technologies in dynamic systems and large-scale complex scenarios. With the rapid development of deep learning and large-scale model technologies, intelligent optimization has achieved remarkable progress across multiple domains. The conference will center on key technologies such as large-scale networks, dynamic optimization, fault diagnosis, and data enhancement, exploring their innovative applications under core challenges including real-time constraints, non-stationary environments, and limited computational resources.
The topics to be covered include, but are not limited to:
Real-time evolutionary optimization methods for dynamic systems
Novel algorithms tailored for specific application scenarios, such as fault diagnosis, indoor positioning, and gesture recognition
New algorithms addressing real-time constraints and non-stationary problems, including evolutionary computation, swarm intelligence, reinforcement learning, and transfer learning
Hybrid algorithms integrating dynamic optimization with other learning techniques
Performance evaluation, theoretical analysis, and algorithm benchmarking
Submission Deadline: June 15, 2025
Special Session Ⅷ: Multimodal Information Perception and Human- Machine Interaction
Session Chair: Prof. Lin Gan——Northwestern Polytechnical University, China
Dr. Zhongjie Li——Northwestern Polytechnical University, China
Keywords: Visual, Auditory, Brain, Information, Perception, Human-Machine Integration
Information: This special session focuses on the forefront technologies related to human-machine multimodal information fusion perception. For example, constructing data fusion models based on visual and auditory perception mechanisms.
The topics to be covered include, but are not limited to:
Visual and auditory perception and human-machine interaction modes
Human-machine integrated information perception
Submission Deadline: June 15, 2025