papers
Publications (3)
cs.CV2025
Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric
Zhichao Zhang, Wei Sun, Xinyue Li +9
AI-driven video generation techniques have made significant progress in recent years. However, AI-generated videos (AGVs) involving human activities often exhibit substantial visua…
cs.CR2026
Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage
Dongdong Zhao, Can Li, Xiang Yao +3
The paper proposes a clean‑label backdoor attack that stays dormant during training and becomes active only after specific camouflage samples are removed via machine unlearning, us…
#backdoor attacks#machine unlearning#clean-label#adversarial machine learning
cs.CV2024
LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models
Qihang Ge, Wei Sun, Yu Zhang +6
The explosive growth of videos on streaming media platforms has underscored the urgent need for effective video quality assessment (VQA) algorithms to monitor and perceptually opti…