arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Nanyang Technological University(南洋理工大学)

2025-12-22 至 2025-12-22 共收录 3
2510.16442 2025-12-22 cs.CV cs.AI

EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning

EDVD-LLaMA: 通过多模态大语言模型推理进行可解释的深度伪造视频检测

Haoran Sun, Chen Cai, Huiping Zhuang, Kong Aik Lee, Lap-Pui Chau, Yi Wang

机构 * Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(电子与电气工程系,香港理工大学) School of Electrical and Electronic Engineering, Nanyang Technological University(电子与电气工程学院,南洋理工大学) Shien-Ming Wu School of Intelligent Engineering, South China University of Technology(智能工程学院,华南理工大学)

AI总结 EDVD-LLaMA通过多模态大语言模型推理实现深度伪造视频检测的可解释性,结合时空特征提取和细粒度推理机制,提升检测准确性与解释可靠性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00724 2025-12-22 cs.CV cs.AI

Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features

Holmes: 通过解耦常见特征实现有效且无害的模型所有权验证以个性化大视觉模型

Linghui Zhu, Yiming Li, Haiqin Weng, Yan Liu, Tianwei Zhang, Shu-Tao Xia, Zhi Wang

机构 * Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院) Tsinghua University(清华大学) Nanyang Technological University(南洋理工大学) Ant Group(蚂蚁集团) Peng Cheng Laboratory(鹏城实验室)

AI总结 本文提出Holmes方法,通过解耦常见特征实现对个性化大视觉模型的无害模型所有权验证,有效检测模型窃取攻击。

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.14280 2025-12-22 cs.CV

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

EasyHOI: 释放大模型潜力以重建真实场景中的手-物体交互

Yumeng Liu, Xiaoxiao Long, Zemin Yang, Yuan Liu, Marc Habermann, Christian Theobalt, Yuexin Ma, Wenping Wang

机构 * The University of Hong Kong(香港大学) ShanghaiTech University(上海科技大学) Hong Kong University of Science and Technology(香港科学大学) Nanyang Technological University(南洋理工大学) Max Planck Institute for Informatics(马克斯·普朗克研究所(信息学)) Texas A&M University(德克萨斯大学奥斯汀分校)

AI总结 EasyHOI利用大模型实现单视角下手-物体交互的重建,通过先验引导优化提升重建精度。

Comments Project page: https://lym29.github.io/EasyHOI-page/

详情

展开后加载摘要…

URL PDF HTML 收藏