ExSample: Efficient Searches on Video Repositories through Adaptive Sampling
Oscar Moll, Favyen Bastani, Sam Madden, Mike Stonebraker, Vijay, Gadepally, Tim Kraska

TL;DR
ExSample is an adaptive sampling framework that efficiently searches for objects in large unindexed video repositories by dynamically prioritizing frames, significantly reducing processing time compared to existing methods.
Contribution
It introduces a novel adaptive sampling approach that dynamically adjusts frame processing based on query and data, enabling faster object search in large video datasets.
Findings
Reduces processing time by up to 6x over random sampling baseline.
Achieves several orders of magnitude speedup over state-of-the-art surrogate model methods.
Effectively prioritizes frames likely to contain objects of interest.
Abstract
Capturing and processing video is increasingly common as cameras become cheaper to deploy. At the same time, rich video understanding methods have progressed greatly in the last decade. As a result, many organizations now have massive repositories of video data, with applications in mapping, navigation, autonomous driving, and other areas. Because state-of-the-art object detection methods are slow and expensive, our ability to process even simple ad-hoc object search queries ('find 100 traffic lights in dashcam video') over this accumulated data lags far behind our ability to collect it. Processing video at reduced sampling rates is a reasonable default strategy for these types of queries, however, the ideal sampling rate is both data and query dependent. We introduce ExSample, a low cost framework for object search over unindexed video that quickly processes search queries by adapting…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
