The 2026 International Conference on Computer Vision and Neural Networks (CVNN 2026) Successfully Held in Chengdu

From April 17 to 19, 2026, the 2026 International Conference on Computer Vision and Neural Networks (CVNN 2026) was successfully held in Chengdu. The conference was organized by Nanchang University, hosted by the Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Computer Interaction and the Information and Communication Branch of State Grid Jiangxi Electric Power Co., Ltd., and supported by the University of Electronic Science and Technology of China. The event took place in person at the Chengdu Liwan International Hotel, bringing together experts, scholars, and industry professionals from around the world in the fields of computer vision, neural networks, and artificial intelligence. The conference featured a series of keynote speeches and oral presentation sessions, with a rich agenda and a vibrant academic atmosphere.

Group Photo

The conference centered on core topics including computer vision, deep learning, multi-modal learning, 3D vision, and neural network architectures, featuring keynote speeches and oral presentations. Three distinguished keynote speakers were specially invited: Prof. Cheng Jian from the University of Electronic Science and Technology of China, Prof. Liu Yue from Beijing Institute of Technology, and Prof. Leng Lu from Nanchang Hangkong University. They delivered outstanding presentations on cutting-edge themes including "High-Precision Human Action Detection in Complex Dynamic Scenes," "Lightweight Single-Image Super-Resolution Reconstruction Methods," and "Multi-Dimensional Evaluation Systems for Recognition Tasks." The event featured a vibrant academic atmosphere with lively discussions and exchanges, fully demonstrating innovative breakthroughs in computer vision and neural network technologies across complex dynamic scenes, lightweight super-resolution reconstruction, and multi-dimensional evaluation for recognition tasks.

Prof. Jian Cheng, University of Electronic Science and Technology of China, China

Title：Research on High-Precision Human Action Detection Methods in Complex Dynamic Scenarios

Prof. Yue Liu, Beijing Institute of Technology, China

Title：Lightweight Single-Image Super-Resolution: Focus-Guided, Texture-Aware, and Infrared Small-Target Enhancement

Prof. Lu Leng, Nanchang Hangkong University, China

Title：Beyond Accuracy: A Multidimensional Evaluation System for Recognition Tasks

Additionally, young scholars from Southwest Petroleum University, Beihang University, Southwest Jiaotong University, and other institutions presented their latest research findings through oral reports, covering directions such as TCN-Transformer-LSTM fusion networks, deep-tissue Raman imaging, and self-powered intelligent transportation perception, showcasing the broad prospects of computer vision and neural network technologies across multiple application fields.

An Huang, Southwest Petroleum University, China

Title：Drilling Kick Prediction Model Based on TCN-Transformer-LSTM Fusion Network(TTL Model)

Difei Li, Beihang University, China

Title：Computer Vision‑Based Image Restoration for Deep‑Tissue Spontaneous Raman Imaging

Jiaoyi Wu, Southwest Jiaotong University, China

Title：Driver abnormal behavior detection enabled self-powered magnetic suspension hybrid wristband and AI for smart transportation

The successful organization of this conference would not have been possible without the dedicated efforts and close collaboration of all host organizations, organizing institutions, supporting units, and staff members. Our sincere gratitude goes to all participating experts, scholars, and volunteers for their support and involvement!