SuperMemory-VQA：面向长期记忆的自我中心视觉问答基准
SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory
AI总结：
提出SuperMemory-VQA数据集，包含52.9小时AI眼镜录制的日常活动及4853个多选问答对，用于评估AI助手在长期记忆任务上的表现，发现现有系统可靠性不足。
摘要：
AI眼镜为AI代理作为个性化记忆助手提供了有吸引力的平台。要真正有用，此类系统必须超越短期视频理解，解决人类在纵向自我中心视频流中因实际、个人或社交目的而经历的记忆缺口。然而，现有的自我中心数据集主要关注动作识别或来自短片的通用问答，衡量的是感知能力而非现实的人类记忆需求。我们引入了SuperMemory-VQA，一个用于评估AI助手在实际长期记忆任务上的自我中心视觉问答（VQA）数据集。它包含52.9小时用AI眼镜记录的日常活动，包括同步的RGB视频、音频转录、眼动追踪、IMU和SLAM轨迹。通过人工验证的标注流程，我们构建了4,853个有依据的问答对，涵盖物体和位置记忆、意图回忆、视觉场景回忆、时间线重建、对话记忆和上下文检索。每个问题以多项选择形式提出，并包含明确的“不可回答”选项以测试幻觉鲁棒性。对领先的代理框架和LLM骨干的基准测试表明，现有系统在现实世界记忆任务上仍远不可靠，凸显了需要新的架构来实现有依据的AI记忆，使其仅在证据充分时才能回答。参与者调查进一步支持我们的问题具有现实性、实用性，并与日常记忆需求一致。
英文摘要：
AI glasses present a compelling platform for AI agents to serve as personalized memory assistants. To be genuinely useful, such systems must move beyond short-term video comprehension and address memory gaps that humans experience for practical, personal, or social purposes over longitudinal egocentric video streams. However, existing egocentric datasets predominantly focus on action recognition or generic QAs from short clips, measuring perceptual capabilities rather than realistic human memory needs. We introduce SuperMemory-VQA, an egocentric visual question answering (VQA) dataset for evaluating AI assistants on practical, long-horizon memory tasks. It contains 52.9 hours of everyday activities recorded with AI glasses, including synchronized RGB video, audio transcription, eye gaze, IMU, and SLAM trajectories. Through a human-verified annotation pipeline, we construct grounded 4,853 question-answer pairs that span object and location memory, intent recall, visual scene recall, timeline reconstruction, conversational memory, and in-context retrieval. Each question is posed as multiple-choice with an explicit "unanswerable" option to test hallucination robustness. Benchmarking leading agentic frameworks and LLM backbones reveals that existing systems remain far from reliable on real-world memory tasks, highlighting the need for new architectures for grounded AI memory that can answer only when evidence is sufficient. A participant survey further supports that our questions are realistic, useful, and aligned with everyday memory needs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
