In recent years, multimodal large models have made significant progress in video understanding and reasoning. However, most of them rely on an offline setting, which assumes that both videos and questions can be fully accessed in advance. In contrast, streaming video question answering scenarios require capturing depen...
Shi-Han Wang, Zhen-Yu Yang, Li-Long Liu et al.· Proceedings of the 34th ACM...· 0 citations
SSNP is proposed, a new prompt tuning approach for FSL that introduces a pair of learnable prompts: one for encoding the relative semantic information in the support set; and another for getting rid of irrelevant distractors within few-shot samples.