Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking
利用文本到图像扩散模型进行无监督视觉目标跟踪
机构 * Information Systems Technology and Design Pillar, Singapore University of Technology and Design(新加坡科技设计大学信息系统技术与设计学院) ; State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University(武汉大学测绘遥感信息工程国家重点实验室) ; Department of Computer Science and Engineering, University at Buffalo, State University of New York(纽约州立大学布法罗分校计算机科学与工程系) ; School of Computer Science, Wuhan University(武汉大学计算机学院)
AI总结 提出Diff-Tracking方法,利用预训练文本到图像扩散模型的跨注意力机制,通过初始提示学习器和在线提示更新器实现无监督目标跟踪。
Comments Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026