4 papers
StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset
Zhengqian Wu, Zhixian Liu, Aodong Chen +6
Video question answering (VideoQA) aims to answer questions about given videos. While existing approaches excel on factoid VideoQA, they struggle with deep video understanding (DVU…
Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection
Zhanhe Lei, Zhongyuan Wang, Jikang Cheng +5
Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work…
Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment
Jiaqing Li, Yajuan Lu, Xiaochuan Shi +3
Vision-Language Models (VLMs) have achieved remarkable success, yet their reliance on massive datasets and unintended memorization of training data raise significant data security…
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…