面向复杂查询的驾驶视频检索与结构化对齐
Driving Video Retrieval for Complex Queries with Structured Grounding
AI总结：
提出STRIVE-D框架，通过弱监督领域视频校准规则、融合视觉语言与关键词检索信号，在驾驶视频检索中实现高达84%的top-1准确率提升。
摘要：
大规模视频检索是自动驾驶中数据整理和安全验证的核心，用户不仅希望找到场景，还希望找到诸如切入和急刹车等动态事件。现有的视觉语言和基于关键词的检索方法常常遗漏这些事件，因为相关的运动可能没有在文本中明确描述或通过词汇重叠捕获。基于规则的检索可以更直接地编码此类事件，但它是脆弱的：生成的或手工编写的规则在假设与真实驾驶数据不匹配时常常失败。我们提出了STRIVE-D，一种针对驾驶视频的数据校准检索框架。它使用弱标记的领域内视频来估计查询规则何时可靠，调整与观测数据不匹配的规则，并将校准后的规则分数与视觉语言和基于关键词的检索信号融合。在三个驾驶基准测试中，包括新发布的DrivingDojo上的人工标注事件数据，STRIVE-D相对于最先进方法在top-1准确率上实现了高达84%的相对改进。
英文摘要：
Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dynamic events such as cut-ins and hard braking. Existing vision-language and keyword-based retrieval methods often miss these events because the relevant motion may not be explicitly described in text or captured by lexical overlap. Rule-based retrieval can encode such events more directly, but it is brittle: generated or hand-written rules often fail when their assumptions do not match real driving data. We propose STRIVE-D, a data-calibrated retrieval framework for driving videos. It uses weakly labeled in-domain videos to estimate when a query rule is reliable, adapt rules that mismatch observed data, and fuse calibrated rule scores with vision-language and keyword-based retrieval signals. Across three driving benchmarks, including newly released human-annotated event data on DrivingDojo, STRIVE-D delivers up to 84% relative improvement in top-1 accuracy over state-of-the-art methods.
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。
