Litcius/Paper detail

FiGO: Fine-Grained Query Optimization in Video Analytics

Jiashen Cao, Karan Sarkar, Ramyad Hadidi, Joy Arulraj, Hyesoon Kim

2022Proceedings of the 2022 International Conference on Management of Data34 citationsDOI

Abstract

Video database management systems (VDBMSs) enable automated analysis of videos at scale using computationally-intensive deep learning models. To reduce the computational overhead of these models, researchers have proposed two techniques: (1) leveraging a specialized, lightweight model to filter out irrelevant frames or to directly answer the query, and (2) using a cascade of models of increasing complexity to answer the query. For both techniques, the query optimizer generates a coarse-grained query plan for the entire video. These techniques suffer from four limitations: (1) lower query accuracy over hard-to-detect predicates, (2) lower filtering efficacy with frequently-occurring objects, (3) lower accuracy due to nontrivial model cascade configuration, and (4) missed optimization opportunities due to coarse-grained planning for the entire video.

Topics & Concepts

Computer scienceQuery optimizationOverhead (engineering)AnalyticsQuery planQuery expansionOnline aggregationFilter (signal processing)Data miningCascadeSargableArtificial intelligenceWeb search queryMachine learningInformation retrievalSearch engineComputer visionOperating systemChromatographyChemistryAdvanced Image and Video Retrieval TechniquesAdvanced Neural Network ApplicationsHuman Pose and Action Recognition
FiGO: Fine-Grained Query Optimization in Video Analytics | Litcius