Kohei Uehara

21 papers A* 1A 2Journal 13Unranked 5
YearRankTypeTitle / Venue / Authors
2025 J jnl
DEJIMA: A Novel Large-scale Japanese Dataset for Image Captioning and Visual Question Answering.
CoRR
Toshiki Katsube, Taiga Fukuhara, Kenichiro Ando, Yusuke Mukuta, Kohei Uehara, Tatsuya Harada
2025 J jnl
Memory-Maze: Scenario Driven Visual Language Navigation Benchmark for Guiding Blind People.
IEEE Robotics Autom. Lett.
Masaki Kuribayashi, Kohei Uehara, Allan Wang, Daisuke Sato, Renato Alexandre Ribeiro, Simon Chu, Shigeo Morishima
2025 J jnl
ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients".
CoRR
Zhongyi Zhou, Kohei Uehara, Haoyu Zhang, Jingtao Zhou, Lin Gu, Ruofei Du, Zheng Xu, Tatsuya Harada
2025 A* conf
WanderGuide: Indoor Map-less Robotic Guide for Exploration by Blind People.
CHI
Masaki Kuribayashi, Kohei Uehara, Allan Wang, Shigeo Morishima, Chieko Asakawa
2025 J jnl
WanderGuide: Indoor Map-less Robotic Guide for Exploration by Blind People.
CoRR
Masaki Kuribayashi, Kohei Uehara, Allan Wang, Shigeo Morishima, Chieko Asakawa
2025 A conf
Zero-Shot Learning for Acoustic Event Classification Using an Attribute Vector and Conditional GAN.
INTERSPEECH
Kohei Uehara, Ryoichi Takashima, Tetsuya Takiguchi
2024 J jnl
Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation.
CoRR
Kohei Uehara, Nabarun Goswami, Hanqin Wang, Toshiaki Baba, Kohtaro Tanaka, Tomohiro Hashimoto, Kai Wang, Rei Ito, Takagi Naoya, Ryo Umagami, Yingyi Wen, Tanachai Anakewat, Tatsuya Harada
2024 — conf
Content-Specific Humorous Image Captioning Using Incongruity Resolution Chain-of-Thought.
NAACL-HLT (Findings)
Kohtaro Tanaka, Kohei Uehara, Lin Gu, Yusuke Mukuta, Tatsuya Harada
2024 J jnl
Learning by Asking Questions for Knowledge-Based Novel Object Recognition.
Int. J. Comput. Vis.
Kohei Uehara, Tatsuya Harada
2024 J jnl
Memory-Maze: Scenario Driven Benchmark and Visual Language Navigation Model for Guiding Blind People.
CoRR
Masaki Kuribayashi, Kohei Uehara, Allan Wang, Daisuke Sato, Simon Chu, Shigeo Morishima
2023 A conf
K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition.
WACV
Kohei Uehara, Tatsuya Harada
2022 J jnl
K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition.
CoRR
Kohei Uehara, Tatsuya Harada
2022 J jnl
Learning by Asking Questions for Knowledge-based Novel Object Recognition.
CoRR
Kohei Uehara, Tatsuya Harada
2022 — conf
Learning to Ask Informative Sub-Questions for Visual Question Answering.
CVPR Workshops
Kohei Uehara, Nan Duan, Tatsuya Harada
2022 — conf
ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer.
WWW (Companion Volume)
Kohei Uehara, Yusuke Mori, Yusuke Mukuta, Tatsuya Harada
2022 J jnl
ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer.
CoRR
Kohei Uehara, Yusuke Mori, Yusuke Mukuta, Tatsuya Harada
2020 — conf
Interactive Video Retrieval with Dialog.
CVPR Workshops
Sho Maeoki, Kohei Uehara, Tatsuya Harada
2019 J jnl
Interactive Video Retrieval with Dialog.
CoRR
Sho Maeoki, Kohei Uehara, Tatsuya Harada
2019 J jnl
Unsupervised Keyword Extraction for Full-sentence VQA.
CoRR
Kohei Uehara, Tatsuya Harada
2018 — conf
Visual Question Generation for Class Acquisition of Unknown Objects.
ECCV (12)
Kohei Uehara, Antonio Tejero-de-Pablos, Yoshitaka Ushiku, Tatsuya Harada
2018 J jnl
Visual Question Generation for Class Acquisition of Unknown Objects.
CoRR
Kohei Uehara, Antonio Tejero-de-Pablos, Yoshitaka Ushiku, Tatsuya Harada