Track 1 | 专题一

Organizers / 组织者

Xuezhuan Zhao (赵雪专)
Associate Professor / 副教授
Zhengzhou University of Aeronautics, China / 郑州航空工业管理学院，中国

Abstract / 论坛简介

Breakthroughs in deep learning and machine learning technologies have propelled transformative advancements in computer vision. Core techniques such as object detection and semantic segmentation are now extensively deployed across critical domains including autonomous driving, smart cities, and aerospace, serving as pivotal enablers for artificial intelligence implementation. This special session is established to consolidate cutting-edge achievements in the field and foster an academic exchange platform. It aims to focus on technological innovation and practical applications within computer vision and intelligent perception, explore pathways to overcome core technical bottlenecks, and promote collaborative innovation among industry, academia, and research institutions.

深度学习与机器学习技术的突破推动计算机视觉领域实现跨越式发展，目标检测、语义分割等核心技术已广泛应用于自动驾驶、智慧城市、航空航天等关键场景，成为人工智能落地的核心支撑。为汇聚该领域前沿成果，搭建学术交流平台，特设立本论坛。论坛旨在聚焦计算机视觉与智能感知领域的技术创新与应用实践，探讨核心技术瓶颈突破路径，促进产学研协同创新。

Topics of Interest / 主题范围

• • Deep learning-driven object detection and tracking / 深度学习驱动的目标检测与跟踪
• • High-resolution image semantic segmentation / 高分辨率图像语义分割
• • Cross-modal visual perception and fusion / 跨模态视觉感知与融合
• • Lightweight visual model design and deployment / 轻量化视觉模型设计与部署
• • Practical research on computer vision in industrial inspection / aerospace / intelligent security / 计算机视觉在工业检测/航空航天/智能安防中的实践研究
• • Optimized application of machine learning in visual tasks / 机器学习在视觉任务中的优化应用