[1Q3-GS-11] Robot and real worlds: Multimodal information

Tue. Jun 9, 2020 1:20 PM - 3:00 PM Room Q (jsai2020online-17)

座長：青島武伸（パナソニック株式会社）

+Add all to schedule

1:20 PM - 1:40 PM

[1Q3-GS-11-01] Category formation of real objects using Multimodal Variational Autoencoder

〇Yuto Yoshida¹, Akira Taniguchi¹, Kaede Hayashi¹, Tadahiro Taniguchi¹ (1. Univ. of Ritsumeikan)

1:40 PM - 2:00 PM

[1Q3-GS-11-02] Influence of Communication on Multimodal Category Formation between Agents

〇Kazuma Furukawa¹, Yoshinobu Hagiwara¹, Tadahiro Taniguchi¹ (1. Univ. of Ritsumeikan)

2:00 PM - 2:20 PM

[1Q3-GS-11-03] Multimodal Learning by Interaction between Probabilistic and Deep Generative Models

〇Ryo Kuniyasu¹, Tomoaki Nakamura¹, Takayuki Nagai², Tadahiro Taniguchi³ (1. The University of Electro-Communications, 2. Osaka University, 3. Ritsumeikan University)

2:20 PM - 2:40 PM

[1Q3-GS-11-04] Cross-modal BERT : Acquisition of Multimodal Representation and Cross-modal Prediction based on Self-Attention

〇Yuta Kyuragi¹, Kazuki Miyazawa¹, Tatsuya Aoki^1,2, Takato Horii¹, Takayuki Nagai^1,2 (1. Osaka University, 2. The University of Electro-Communications)

2:40 PM - 3:00 PM

[1Q3-GS-11-05] Sentence Generation for Fetching Instruction based on Multimodal Attention Branch Network

〇Tadashi Ogura¹, Aly Magassouba¹, Komei Sugiura¹, Tsubasa Hirakawa², Takayoshi Yamashita², Hironobu Fujiyoshi², Hisashi Kawai¹ (1. National Institute of Information and Communications Technology, 2. Chubu University)

Session information