Across Images and Graphs for Question Answering
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AGCD72W98" target="_blank" >RIV/00216208:11320/25:GCD72W98 - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200447291&doi=10.1109%2fICDE60146.2024.00112&partnerID=40&md5=2c3d78ee352cdb18e861e0fb7c79f868" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200447291&doi=10.1109%2fICDE60146.2024.00112&partnerID=40&md5=2c3d78ee352cdb18e861e0fb7c79f868</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICDE60146.2024.00112" target="_blank" >10.1109/ICDE60146.2024.00112</a>
Alternative languages
Result language
angličtina
Original language name
Across Images and Graphs for Question Answering
Original language description
Cross-source query serves as a proxy for scene understanding to support many web applications such as rec-ommendation systems, e-commerce, and e-learning applications. In this paper, we propose SVQA that semantically combines the knowledge from available images and graphs to answer the complex question. To this end, we design a graph-based method to unify various data sources into one representation. We then develop a complex question parse method that utilizes the structure of languages to transform the query into a query graph. A graph query engine that performs the query graph over the unified data source while optimizing the query process. To evaluate the proposed system, we build a vanilla dataset called MVQA and show that the state-of-the-art (SOTA) VQA models fail to perform our task. The comprehensive evaluations show that the proposed SVQA is able to reason implicit relationships over multiple images and external knowledge to correctly answer a complex query. We hope that our first attempt provides researchers with a fresh taste of multimodal data analysis. © 2024 IEEE.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proc Int Conf Data Eng
ISBN
979-835031715-2
ISSN
1084-4627
e-ISSN
—
Number of pages
14
Pages from-to
1366-1379
Publisher name
IEEE Computer Society
Place of publication
—
Event location
Utrecht
Event date
Jan 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—