Self-supervised learning for visual summary identification in scientific publications

Shintaro Yamamoto*, Anne Lauscher, Simone Paolo Ponzetto, Goran Glavaš, Shigeo Morishima

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review


Providing visual summaries of scientific publications can increase information access for readers and thereby help deal with the exponential growth in the number of scientific publications. Nonetheless, efforts in providing visual publication summaries have been few and far apart, primarily focusing on the biomedical domain. This is primarily because of the limited availability of annotated gold standards, which hampers the application of robust and high-performing supervised learning techniques. To address these problems we create a new benchmark dataset for selecting figures to serve as visual summaries of publications based on their abstracts, covering several domains in computer science. Moreover, we develop a self-supervised learning approach, based on heuristic matching of inline references to figures with figure captions. Experiments in both biomedical and computer science domains show that our model is able to outperform the state of the art despite being self-supervised and therefore not relying on any annotated training data.

Original languageEnglish
Pages (from-to)5-19
Number of pages15
JournalCEUR Workshop Proceedings
Publication statusPublished - 2021
Event11th International Workshop on Bibliometric-Enhanced Information Retrieval, BIR 2021 - Viruta, Lucca, Italy
Duration: 2021 Apr 1 → …


  • Multimodal retrieval
  • Scientific publication mining
  • Visual summary identification

ASJC Scopus subject areas

  • Computer Science(all)


Dive into the research topics of 'Self-supervised learning for visual summary identification in scientific publications'. Together they form a unique fingerprint.

Cite this