Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding

Understand

Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows.

• A common workaround is to compress long videos into a handful of representative frames via retrieval or summarization.
• However, most existing pipelines score frames in isolation, implicitly assuming that frame-level saliency is sufficient for downstream reasoning.
• This often yields redundant selections, fragmented temporal evidence, and weakened narrative grounding for long-form video question answering.