Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine

Summary: Identifies cost and deployment pain in DNN video analytics and presents BlazeIt—an optimizing engine with FrameQL to automate and scale video-analytics pipelines. Demos FrameQL plus ML-debugging and optimizer primitives to make large-scale video queries feasible and outlines remaining systems challenges. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 324
Venue: CIDR
Year: 2019
Pagerank: 0.0001022751
Overall Rank: 1,607 | 88.98%
DOI: -

Incoming Non-self Citations Over Time

Authors

1. Daniel Kang (Stanford University)
2. Peter Bailis (Stanford University)
3. Matei Zaharia (Stanford University)

BibTeX Citation

@inproceedings{kang_cidr19,
        address = {Amsterdam, Netherlands},
        series = {{CIDR} '19},
        title = {{Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine}},
        booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
        author = {Kang, Daniel and Bailis, Peter and Zaharia, Matei},
        year = {2019}
}

Incoming Citations (Sorted by Pagerank)

Showing 12 of 12 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
569	BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics	2020	VLDB	0.00016348191
1,042	MIRIS: Fast Object Track Queries in Video	2020	SIGMOD	0.00012451966
2,384	DeepLens: Towards a Visual Data Management System	2019	CIDR	8.6494525e-05
3,253	Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics	2021	VLDB	7.5936939e-05
3,365	Spatial and Temporal Constrained Ranked Retrieval over Videos	2022	VLDB	7.4763252e-05
3,756	Vaas: Video Analytics At Scale	2020	VLDB	7.1487427e-05
4,298	OTIF: Efficient Tracker Pre-processing over Large Video Datasets	2022	SIGMOD	6.7750533e-05
4,429	Evaluating Temporal Queries Over Video Feeds	2021	SIGMOD	6.7092231e-05
6,043	Mixer: Efficiently Understanding and Retrieving Visual Content at Web-scale	2021	VLDB	5.9966613e-05
8,331	TQVS: Temporal Queries over Video Streams in Action	2020	SIGMOD	5.4520778e-05
8,518	DeepVQL: Deep Video Queries on PostgreSQL	2023	VLDB	5.4119882e-05
11,268	Optimizing Video Queries with Declarative Clues	2024	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 6 of 6 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
284	NoScope: Optimizing Neural Network Queries over Video at Scale	2017	VLDB	0.00022370521
295	Accelerating Machine Learning Inference with Probabilistic Predicates	2018	SIGMOD	0.00022238183
353	The Query By Image Content (QBIC) System	1995	SIGMOD	0.00020370587
2,384	DeepLens: Towards a Visual Data Management System	2019	CIDR	8.6494525e-05
2,532	STRG-Index: Spatio-Temporal Region Graph Indexing for Large Video Databases	2005	SIGMOD	8.4572502e-05
5,737	Kyrix: Interactive Visual Data Exploration at Scale	2019	CIDR	6.1049023e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	9,464	Self-Enhancing Video Data Management System for Compositional Events with Large Language Models	2025	SIGMOD
2	7,739	Video-zilla: An Indexing Layer for Large-Scale Video Analytics	2022	SIGMOD
3	8,518	DeepVQL: Deep Video Queries on PostgreSQL	2023	VLDB
4	5,827	Top-K Deep Video Analytics: A Probabilistic Approach	2021	SIGMOD
5	3,253	Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics	2021	VLDB
6	4,007	Optimizing Video Analytics with Declarative Model Relationships	2023	VLDB
7	2,384	DeepLens: Towards a Visual Data Management System	2019	CIDR
8	3,410	SVQ: Streaming Video Queries	2019	SIGMOD
9	11,268	Optimizing Video Queries with Declarative Clues	2024	VLDB
10	569	BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics	2020	VLDB