Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks read more
Pretraining-Based Natural Language Generation for Text Summarization ～BERTから考える要約のこれまでとこれから～ read more
Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos (AAAI 2019) read more
