| 2026 | ACL | ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients". | Zhongyi Zhou, Kohei Uehara, Haoyu Zhang, Jingtao Zhou, Lin Gu, Ruofei Du, Zheng Xu, Tatsuya Harada |
| 2026 | LREC | DEJIMA: A Novel Large-scale Japanese Dataset for Image Captioning and Visual Question Answering. | Toshiki Katsube, Taiga Fukuhara, Kenichiro Ando, Yusuke Mukuta, Kohei Uehara, Tatsuya Harada |
| 2025 | CHI | WanderGuide: Indoor Map-less Robotic Guide for Exploration by Blind People. | Masaki Kuribayashi, Kohei Uehara, Allan Wang, Shigeo Morishima, Chieko Asakawa |
| 2025 | Interspeech | Zero-Shot Learning for Acoustic Event Classification Using an Attribute Vector and Conditional GAN. | Kohei Uehara, Ryoichi Takashima, Tetsuya Takiguchi |
| 2024 | NAACL | Content-Specific Humorous Image Captioning Using Incongruity Resolution Chain-of-Thought. | Kohtaro Tanaka, Kohei Uehara, Lin Gu, Yusuke Mukuta, Tatsuya Harada |
| 2023 | WACV | K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition. | Kohei Uehara, Tatsuya Harada |
| 2022 | CVPR | Learning to Ask Informative Sub-Questions for Visual Question Answering. | Kohei Uehara, Nan Duan, Tatsuya Harada |
| 2022 | WWW | ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer. | Kohei Uehara, Yusuke Mori, Yusuke Mukuta, Tatsuya Harada |
| 2020 | CVPR | Interactive Video Retrieval with Dialog. | Sho Maeoki, Kohei Uehara, Tatsuya Harada |
| 2018 | ECCV | Visual Question Generation for Class Acquisition of Unknown Objects. | Kohei Uehara, Antonio Tejero-de-Pablos, Yoshitaka Ushiku, Tatsuya Harada |