MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
[Widzenie komputerowe] Autorzy: Guangzhi Xiong, Xinyuan Zhang, Xiao Yang i 14 więcej
Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessing raw clips for every query becomes computationally prohibitive. Memory systems offer a scalable alternative by compacting videos into text representations, but often fail on practical benchmarks: either the memory does not preserve key evidence, or the retriever fails to locate relevant entries due to retrieval competition in growing search spaces. To address these challenges, we introduce MemLife, a multimodal memory system that constructs entity-grounded, first-person text episodes and retrieves them via a time-indexed agentic reader. Without training or query-time video access, MemLife improves over the strongest training-free baseline by 4.6--12.0% across four long-horizon benchmarks. To further improve …
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe