Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking 文章

ArXiv CS.CV2026-05-27NEWSen作者: Zhengbo Zhang, Zhigang Tu, Junsong Yuan, De Wen Soh, Bo Du
查看原文 →
关系图谱

Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking · 相关技术

相关技术

ginORMODE研究法辛烷值扩散模型text-to-image diffusiondiffusion modelsUCTText-to-imageStanSEMPromptPPROWLOTANPUHISForFOLEffort Metric AttentionENADiffusionCamouflaged object detectionARGANNAGIiOS