Craw: A Unified and Efficient Querying Framework for Large-Scale Video Datasets

Summary: Craw unifies existence, dynamic, and similarity queries over large-scale video via semantic units, semantic-preserving segmentation, and a hybrid inverted/cluster index. It avoids VLM-scale costs, achieving up to 100× lower latency than prior systems. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID: ha40643ea69c3ad3a
Venue: VLDB
Year: 2026
Pagerank: 4.9793485e-05
Overall Rank: 10,839 | 27.13%
DOI: 10.14778/3836663.3836666

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Ziqi Zhou (Nanchang University)
2. Hanjian Jiang (Nanchang University)
3. Zihao Zeng (Nanchang University)
4. Xupuzhe Shao (Nanchang University)
5. Zichen Xu (Nanchang University)

BibTeX Citation

@article{zhou_vldb26,
        title = {{Craw: A Unified and Efficient Querying Framework for Large-Scale Video Datasets}},
        author = {Zhou, Ziqi and Jiang, Hanjian and Zeng, Zihao and Shao, Xupuzhe and Xu, Zichen},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {11},
        pages = {2964--2977},
        doi = {10.14778/3836663.3836666},
        url = {https://doi.org/10.14778/3836663.3836666},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
194	Milvus: A Purpose-Built Vector Data Management System	2021	SIGMOD	0.00025636725
271	NoScope: Optimizing Neural Network Queries over Video at Scale	2017	VLDB	0.00022560564
541	BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics	2020	VLDB	0.00016657685
1,024	MIRIS: Fast Object Track Queries in Video	2020	SIGMOD	0.00012430491
2,501	Trajectory Simplification: On Minimizing the Direction-based Error	2015	VLDB	8.3808899e-05
2,787	EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views	2022	SIGMOD	8.0158999e-05
3,884	FiGO: Fine-Grained Query Optimization in Video Analytics	2022	SIGMOD	6.948464e-05
3,948	OTIF: Efficient Tracker Pre-processing over Large Video Datasets	2022	SIGMOD	6.9053923e-05
5,211	Seiden: Revisiting Query Processing in Video Database Systems	2023	VLDB	6.2253642e-05
7,009	Video-zilla: An Indexing Layer for Large-Scale Video Analytics	2022	SIGMOD	5.6222568e-05
7,447	EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions	2023	VLDB	5.5240718e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	3,429	SVQ: Streaming Video Queries	2019	SIGMOD
2	11,310	Deja Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse	2025	VLDB
3	3,411	Spatial and Temporal Constrained Ranked Retrieval over Videos	2022	VLDB
4	2,710	Panorama: A Data System for Unbounded Vocabulary Querying over Video	2020	VLDB
5	10,107	TVM: A Tile-based Video Management Framework	2024	VLDB
6	4,456	Efficient and Cost-effective Techniques for Browsing and Indexing Large Video Databases	2000	SIGMOD
7	4,495	Evaluating Temporal Queries Over Video Feeds	2021	SIGMOD
8	11,596	Optimizing Video Queries with Declarative Clues	2024	VLDB
9	9,645	Self-Enhancing Video Data Management System for Compositional Events with Large Language Models	2025	SIGMOD
10	7,009	Video-zilla: An Indexing Layer for Large-Scale Video Analytics	2022	SIGMOD