Multi-task learning of hierarchical vision-language representation

Duy Kien Nguyen, Takayuki Okatani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

28 Citations (Scopus)


It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and trained them on its dedicated datasets. Although this approach has seen a certain degree of success, it comes with difficulties of understanding relations among different tasks and transferring the knowledge learned for a task to others. We propose a multi-task learning approach that enables to learn vision-language representation that is shared by many tasks from their diverse datasets. The representation is hierarchical, and prediction for each task is computed from the representation at its corresponding level of the hierarchy. We show through experiments that our method consistently outperforms previous single-task-learning methods on image caption retrieval, visual question answering, and visual grounding. We also analyze the learned hierarchical representation by visualizing attention maps generated in our network.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PublisherIEEE Computer Society
Number of pages10
ISBN (Electronic)9781728132938
Publication statusPublished - 2019 Jun
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
Duration: 2019 Jun 162019 Jun 20

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919


Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/TerritoryUnited States
CityLong Beach


  • Categorization
  • Deep Learning
  • Recognition: Detection
  • Representation Learning
  • Retrieval
  • Vision + Language


Dive into the research topics of 'Multi-task learning of hierarchical vision-language representation'. Together they form a unique fingerprint.

Cite this