Scholarlink

We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module. On the QAEgo4D-Closed benchmark, our best configuration attains 56.0% accuracy with \(\sim \) 3.6 kB per minute storage, matching the performance of dedicated state-of-the-art systems while being \(10^{4}\) – \(10^{5}\) times more memory-efficient. Extensive ablations provide insights into the role of each component and design choice and highlight directions for improvement in future research.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Giuseppe Lando,
  • Rosario Forte,
  • Giovanni Maria Farinella,
  • Antonino Furnari

摘要

We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module. On the QAEgo4D-Closed benchmark, our best configuration attains 56.0% accuracy with \(\sim \) 3.6 kB per minute storage, matching the performance of dedicated state-of-the-art systems while being \(10^{4}\) – \(10^{5}\) times more memory-efficient. Extensive ablations provide insights into the role of each component and design choice and highlight directions for improvement in future research.