1 code implementation • 7 Feb 2024 • Ryutaro Asahara, Masaki Takahashi, Chiho Iwahashi, Michimasa Inaba
Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences. Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for advanced information. This study proposed a novel framework SumRec for recommending information from open-domain chat dialogue. The study also examined the framework using ChatRec, a newly constructed dataset for training and evaluation.
no code implementations • 14 Jul 2023 • Ryosuke Korekata, Motonari Kambara, Yu Yoshida, Shintaro Ishikawa, Yosuke Kawasaki, Masaki Takahashi, Komei Sugiura
The results show that our method outperforms the baseline method in terms of language comprehension accuracy.
no code implementations • 2 Aug 2022 • Hiroyasu Akada, Jian Wang, Soshi Shimada, Masaki Takahashi, Christian Theobalt, Vladislav Golyanik
We present UnrealEgo, i. e., a new large-scale naturalistic dataset for egocentric 3D human pose estimation.
Ranked #4 on Egocentric Pose Estimation on UnrealEgo