research-article

EQUI-VOCAL Demonstration: Synthesizing Video Queries from User Interactions

Authors:

Dong He,

Magdalena BalazinskaAuthors Info & Claims

Proceedings of the VLDB Endowment, Volume 16, Issue 12

Pages 3978 - 3981

https://doi.org/10.14778/3611540.3611600

Published: 01 August 2023 Publication History

Get Access

Abstract

We demonstrate EQUI-VOCAL, a system that synthesizes compositional queries over videos from user feedback. EQUI-VOCAL enables users to query a video database for complex events by providing a few positive and negative examples of what they are looking for and labeling a small number of additional system-selected examples. Using those user inputs, EQUI-VOCAL synthesizes declarative queries that can then retrieve additional instances of the desired events. The demonstration makes two contributions: it introduces EQUI-VOCAL's graphical user interface and enables conference attendees to experiment with EQUI-VOCAL on a variety of queries. Both enable users to gain a better understanding of EQUI-VOCAL's query synthesis approach and to explore the impact of hyperparameters and label noise on system performance.

References

[1]

Daren Chao et al. 2020. SVQ++: Querying for Object Interactions in Video Streams. In SIGMOD. 2769--2772.

Google Scholar

[2]

Yueting Chen et al. 2022. Spatial and Temporal Constrained Ranked Retrieval over Videos. PVLDB 15, 11 (2022), 3226--3239.

Google Scholar

[3]

Maureen Daum et al. 2022. VOCAL: Video Organization and Interactive Compositional AnaLytics. In CIDR.

Google Scholar

[4]

Maureen Daum et al. 2023. VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building [Technical Report]. arXiv preprint arXiv:2303.04068 (2023).

Google Scholar

[5]

Daniel Y. Fu et al. 2019. Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels. arXiv preprint arXiv:1910.02993 (2019).

Google Scholar

[6]

Mohammad Reza Karimi et al. 2021. Online Active Model Selection for Pre-trained Classifiers. In AISTATS, Vol. 130. 307--315.

Google Scholar

[7]

Ranjay Krishna et al. 2017. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. IJCV 123, 1 (2017), 32--73.

Digital Library

Google Scholar

[8]

Jie Lei et al. 2021. QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries. In NeurIPS.

Google Scholar

[9]

Yao Lu et al. 2018. Accelerating Machine Learning Inference with Probabilistic Predicates. In SIGMOD. 1493--1508.

Google Scholar

[10]

Stephen Mell et al. 2021. Synthesizing Video Trajectory Queries. In AIPLANS Workshop.

Google Scholar

[11]

Oscar R. Moll et al. 2022. ExSample: Efficient Searches on Video Repositories through Adaptive Sampling. In ICDE. 3065--3077.

Google Scholar

[12]

Kexin Yi et al. 2020. CLEVRER: Collision Events for Video Representation and Reasoning. In ICLR.

Google Scholar

[13]

Enhao Zhang et al. 2023. EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions. PVLDB 16, 12 (2023).

Google Scholar

Recommendations

EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions

We introduce EQUI-VOCAL: a new system that automatically synthesizes queries over videos from limited user interactions. The user only provides a handful of positive and negative examples of what they are looking for. EQUI-VOCAL utilizes these initial ...
Scalable Equi-Join Queries over Encrypted Database
CCS '24: Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security

Secure join queries over encrypted databases, the most expressive class of SQL queries, have attracted extensive attention recently. The state-of-the-art JXT (Jutla et al. ASIACRYPT 2022) enables join queries on encrypted relational databases without pre-...
Efficient top-k retrieval for user preference queries
SAC '11: Proceedings of the 2011 ACM Symposium on Applied Computing

Efficient retrieval of the most relevant (i.e. top-k) tuples is an important requirement in information systems which access large amounts of data. In general answering a top-k query request means to retrieve the k-objects which score best for an ...

Comments

Information & Contributors

Information

Published In

cover image Proceedings of the VLDB Endowment

Proceedings of the VLDB Endowment Volume 16, Issue 12

August 2023

685 pages

ISSN:2150-8097

Editors:
Georgia Koutrika
Athena Research Center
,
Jun Yang
Duke University

Issue’s Table of Contents

Publisher

VLDB Endowment

Publication History

Published: 01 August 2023

Published in PVLDB Volume 16, Issue 12

Check for updates

Badges

Artifacts Available / v1.1

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
96
Total Downloads

Downloads (Last 12 months)64
Downloads (Last 6 weeks)2

Reflects downloads up to 22 Dec 2024

Other Metrics

View Author Metrics

Citations

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Recommendations

EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions

Scalable Equi-Join Queries over Encrypted Database

Efficient top-k retrieval for user preference queries