Special Session Ⅷ
Computer Vision (Submission Deadline: August 31, 2026)
计算机视觉
| Chair: | Co-chair: |
 |
 |
| Songlin Du Southeast University, China |
Guobao Xiao Tongji University, China |
| Keywords: | |
| · Computer Vision (计算机视觉) · Digital Image Processing (数字图像处理) · Video Analysis (视频分析) · 3D Vision and Reconstruction (三维视觉与重建) · Vision Foundation Models (视觉大模型) |
|
| Topics (include but are not limited to): | |
| · Image and video understanding (图像与视频理解) · 3D vision and reconstruction (三维视觉与重建) · Multi-view geometry (多视角几何) · Object detection and recognition (目标检测与识别) · Semantic segmentation (语义分割) · Visual tracking (视觉跟踪) · Visual generation and diffusion models (视觉生成与扩散模型) · Vision foundation models (视觉大模型) · Multimodal learning (多模态学习) · Cross-modal understanding (跨模态理解) · Dynamic scene modeling (动态场景建模) · Multi-agent collaborative perception (多主体协同感知) · World models and visual consistency (世界模型与视觉一致性) · Self-supervised learning (自监督学习) · Real-time and efficient vision algorithms (实时高效视觉算法) · Robustness and generalization (系统鲁棒性与泛化能力) · Autonomous driving (自动驾驶) · Robotics (机器人) · Industrial inspection (工业检测) |
|
| Summary: | |
| · This track focuses on cutting-edge theories and key technologies in computer vision. With the rapid advancement of intelligent perception and automation applications, visual understanding has become a fundamental pillar supporting decision-making in artificial intelligence systems. The track is intended for researchers, engineers, and industry practitioners working in computer vision and related fields, with particular interest in those engaged in multi-view perception, dynamic scene modeling, and vision foundation models. By bringing together the latest research advances and practical applications, this track aims to promote the integration of algorithmic innovation with real-world deployment, foster interdisciplinary collaboration, and enhance the robustness and generalization capabilities of vision systems in complex environments. | |
|
· 本专题聚焦计算机视觉领域的前沿理论与关键技术，在智能感知与自动化应用快速发展的背景下，视觉理解已成为支撑人工智能系统决策能力的核心基础。本专题面向从事计算机视觉及相关领域研究的学者、工程师以及产业界技术人员，尤其欢迎关注多视角感知、动态场景建模与视觉大模型的研究者参与交流。通过汇聚最新研究成果与应用实践，专题旨在推动算法创新与系统落地相结合，促进跨领域融合，提升复杂环境下视觉系统的鲁棒性与泛化能力。 |
|