Presentation information

International Session

International Session (Work in progress) » EW-1 Knowledge engineering

[1N4-IS-1a] Knowledge engineering (1/3)

Tue. Jun 8, 2021 5:20 PM - 7:00 PM Room N (IS room)

Chair: Akinori Abe (Chiba University)

6:20 PM - 6:40 PM

[1N4-IS-1a-04] Semantic and Topic fused Multimodal Transformer

〇Shuhei Tateishi1, Sohei Okui1, Hirofumi Yashima1, Makoto Nakatsuji1 (1. NTT Resonant, Inc.)

Keywords:Multimodal, Transformer, Semantic

The human behaviors observed in multi modalities are naturally related with each other and many AI/ML methods try to catch such implicit relationships to enhance the prediction accuracies on users' behaviors.
Ordinal methods, however, do not try to use the explicit relationships (e.g. taxonomy of emotions) across the modalities.
In this paper, we suggest a new hypothesis for measuring the relevances across the modalities to improve accuracies.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.