3 papers
cs.CV2025
SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition
Qilang Ye, Yu Zhou, Lian He +10
Large Language Models (LLMs) hold rich implicit knowledge and powerful transferability. In this paper, we explore the combination of LLMs with the human skeleton to perform action…
cs.CV2025
When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion?
Qilang Ye, Wei Zeng, Meng Liu +4
Can Multimodal Large Language Models (MLLMs) discern confused objects that are visually present but audio-absent? To study this, we introduce a new benchmark, AV-ConfuseBench, whic…
cs.LG2024
PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks
Jin Li, Zitong Yu, Ziqiang He +2
Imperceptible adversarial attacks have recently attracted increasing research interests. Existing methods typically incorporate external modules or loss terms other than a simple $…