2026 International Conference on Computer Perception and Neural Networks

The 2026 International Conference on Computer Perception and Neural Networks (CPNN 2026) will be held in Shenzhen, China, from August 28 to 30, 2026. Sponsored by the Guangdong Digital Intelligence Science and Technology Association, the conference aims to provide a high-level international forum for researchers, scholars, and professionals to present and exchange recent advances in computer perception and neural network technologies.

CPNN 2026 focuses on two main research tracks: Computer Perception and Vision Systems and Neural Networks and Learning Algorithms. The conference will cover key topics including computer vision, image and video analysis, object detection and tracking, multimodal perception, deep learning methods, neural network architectures, representation learning, and brain-inspired computing. By addressing both theoretical foundations and practical systems, the conference highlights the close integration of perception and learning in modern intelligent systems.

The conference seeks to promote in-depth academic exchange, foster interdisciplinary collaboration, and encourage innovation in related research fields. Researchers, engineers, and industry practitioners are warmly invited to participate in CPNN 2026 to share their latest research findings, discuss emerging challenges, and contribute to the continued development of computer perception and neural network technologies.

Full Paper Submission Date: June 01, 2026

Registration Deadline: July 03, 2026

Final Paper Submission Date: July 27, 2026

Conference Dates: August 28-30, 2026

Topics of interest for submission are as followed:

Track 1: Computer Perception and Vision Systems

Track 2: Neural Networks and Learning Algorithms

Computer vision and pattern recognition
Image and video analysis
Object detection and tracking
Scene understanding and visual perception
3D vision and point cloud processing
Multimodal perception and sensor fusion
Human–computer interaction and visual interfaces
Biometric recognition and visual security
Perception for robotics and autonomous systems

Neural network architectures and models
Deep learning methods and optimization
Convolutional, recurrent, and graph neural networks
Representation learning and feature extraction
Self-supervised and reinforcement learning
Robust, efficient, and interpretable neural networks
Distributed and federated learning
Brain-inspired and neuromorphic computing
Neural networks for perception and intelligent systems

Sponsored By
Guangdong Digital Intelligence Science and Technology Association (GDISTA) 广东省数智科技研究会

Supported By
Shenzhen Polytechnic University

South China University of Technology	Southern University of Science and Technology


Guangdong Computer Academy	Shenzhen Technology University


Guangdong University of Technology	Macao Technology And Cultural Exchange Association