GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models
GA2-CLIP:通用属性锚点用于视频-语言模型高效提示微调
机构 * Shandong Provincial Key Laboratory of New Power Distribution & Utilization Technology and Equipment, School of Electrical and Electronic Engineering, Shandong University of Technology(山东省新型电力分布与利用技术及设备重点实验室,山东理工大学电气与电子工程学院) ; School of Computer Science and Technology, Shandong University of Technology(山东理工大学计算机科学与技术学院) ; School of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(南京航空航天大学人工智能学院) ; Pillar of Information Systems Technology and Design, Singapore University of Technology and Design(新加坡科技设计大学信息系统技术与设计 pillar) ; School of Control Science and Engineering, Shandong University(山东大学控制科学与工程学院)
专题命中 其他视频模型 :video-language(title);分类 cs.CV
AI总结 GA2-CLIP通过引入外部监督提示和无关视频集,优化视频任务中V-L模型的泛化性能,防止语义空间过拟合,提升模型在新类别预测上的表现。
Comments Technical Report