2 papers
cs.CV2025
Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection
Shibo Yao, Renshuai Tao, Xiaolong Zheng +2
Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot" task, training on images generated by known models but generalizing to unknown ones. A key r…
cs.CV2024
FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos
Zhengqian Wu, Ruizhe Li, Zijun Xu +3
Video question answering (VideoQA) aims to answer natural language questions according to the given videos. Although existing models perform well in the factoid VideoQA task, they…