6 papers · 1 filter
Retrieval-Driven Training-Free AI-Generated Video Attribution
Renxi Cheng, Chaolei Han, Jie Gui +1
AI-generated videos are becoming increasingly realistic and difficult to distinguish from authentic ones, which facilitates malicious misuse and poses growing threats to cybersecur…
OZ-TAL: Online Zero-Shot Temporal Action Localization
Chaolei Han, Hongsong Wang, Xin Gong +1
Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent adva…
Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution
Hongsong Wang, Renxi Cheng, Chaolei Han +1
With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic i…
LOTA: Bit-Planes Guided AI-Generated Image Detection
Hongsong Wang, Renxi Cheng, Yang Zhang +2
The rapid advancement of GAN and Diffusion models makes it more difficult to distinguish AI-generated images from real ones. Recent studies often use image-based reconstruction err…
Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
Jidong Kuang, Hongsong Wang, Chaolei Han +2
Zero-shot action recognition, which addresses the issue of scalability and generalization in action recognition and allows the models to adapt to new and unseen actions dynamically…
Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
Chaolei Han, Hongsong Wang, Jidong Kuang +2
Existing zero-shot temporal action detection (ZSTAD) methods predominantly use fully supervised or unsupervised strategies to recognize unseen activities. However, these training-b…