From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms

  • 类型:arxiv
  • 标识:2608.24877
  • 链接:https://arxiv.org/abs/2608.24877
  • 主分类:multimodal
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This survey is the first to systematically study smart glasses through a unified framework, formalizing first-person data flow and constrained task utility, and introducing an L0-L5 framework spanning capture, reactive perception, contextual assistance, persistent state, governed action, and embodied coupling.
  • OpenAlex ID:W7204228371
  • OpenAlex DOI:10.48550/arxiv.2608.24877
  • DOI:10.48550/arxiv.2608.24877
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/2608.24877
  • OpenAlex更新:2026-08-31
  • 待LLM分类:否
  • 标题中文:从看见到行动:智能眼镜作为第一人称智能平台
  • TLDR中文:本综述首次以统一框架系统研究智能眼镜,形式化第一人称数据流与受限任务效用,并提出覆盖采集、反应式感知、上下文辅助、持续状态、受控行动与具身耦合的 L0–L5 框架。
  • 来源文件:
  • /inbox/tom/_candidates/2026-08-26-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]