7 papers
4D Reconstruction from Sparse Dynamic Cameras
Kazuki Ozeki, Shun Kenney, Yuto Shibata +6
Although dynamic 3D (i.e., 4D) reconstruction from a monocular dynamic camera has recently advanced, it remains fundamentally limited by depth ambiguity. In this paper, we focus on…
Sign-to-Speech Prosody Transfer via Sign Reconstruction-based GAN
Toranosuke Manabe, Yuto Shibata, Shinnosuke Takamichi +1
Deep learning models have improved sign language-to-text translation and made it easier for non-signers to understand signed messages. When the goal is spoken communication, a naiv…
Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
Yuto Shibata, Kashu Yamazaki, Lalit Jayanti +3
Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking within physics engines (GMT) have…
Formula-Supervised Sound Event Detection: Pre-Training Without Real Data
Yuto Shibata, Keitaro Tanaka, Yoshiaki Bando +3
In this paper, we propose a novel formula-driven supervised learning (FDSL) framework for pre-training an environmental sound analysis model by leveraging acoustic signals parametr…
BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds
Yuto Shibata, Yusuke Oumi, Go Irie +3
We propose BGM2Pose, a non-invasive 3D human pose estimation method using arbitrary music (e.g., background music) as active sensing signals. Unlike existing approaches that signif…
Acoustic-based 3D Human Pose Estimation Robust to Human Position
Yusuke Oumi, Yuto Shibata, Go Irie +3
This paper explores the problem of 3D human pose estimation from only low-level acoustic signals. The existing active acoustic sensing-based approach for 3D human pose estimation i…