analiza aiqbench
This paper introduces STRIVE-D, a novel framework that enhances video retrieval in autonomous driving by calibrating rule-based logic with vision-language models to better detect dynamic safety events like cut-ins. By fusing these adaptive signals with traditional keyword methods, the system achieves significant accuracy gains over existing state-of-the-art approaches on major benchmarks. This advancement directly addresses critical data curation and safety validation challenges within the self-driving vehicle ecosystem.
Driving Video Retrieval for Complex Queries with Structured Grounding
arXiv:2606.09109v2 Announce Type: replace-cross Abstract: 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.
Abstract: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.
Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR); Machine Learning (cs.LG)
arXiv:2606.09109 [cs.CV]
(or arXiv:2606.09109v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.09109 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 253 cuvinte
Subiecte conexe
Driving Video Retrieval for Complex Queries with Structured Grounding
arXiv · 9 iun. 2026
Modernizing and scaling support operations with generative AI on AWS
AWS · 2 sept. 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · 15 iul. 2026
Presentation: Engineering AI for Creativity and Curiosity on Mobile
InfoQ · 21 iul. 2026