Search Results - "Yonetani, Ryo"

Future Person Localization in First-Person Videos by Yagi, Takuma, Mangalam, Karttikeya, Yonetani, Ryo, Sato, Yoichi

“…We present a new task that predicts future locations of people observed in first-person videos. Consider a first-person video stream continuously recorded by a…”
Get full text

L2B: Learning to Balance the Safety-Efficiency Trade-off in Interactive Crowd-aware Robot Navigation by Nishimura, Mai, Yonetani, Ryo

“…This work presents a deep reinforcement learning framework for interactive navigation in a crowded place. Our proposed Learning to Balance (L2B) framework…”
Get full text

Recognizing Micro-Actions and Reactions from Paired Egocentric Videos by Yonetani, Ryo, Kitani, Kris M., Sato, Yoichi

“…We aim to understand the dynamics of social interactions between two people by recognizing their actions and reactions using a head-mounted camera. Our work…”
Get full text

Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People by Nitta, Yasuhiro, Isogawa, Mariko, Yonetani, Ryo, Sugimoto, Maki

“…This paper examines an importance rank learning method of objects in urban scenes for assisting visually impaired people. Object detection methods have been…”
Get full text

Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge by Nishio, Takayuki, Yonetani, Ryo

“…We envision a mobile edge computing (MEC) framework for machine learning (ML) technologies, which leverages distributed client data and computation resources…”
Get full text

Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data by Yoshida, Naoya, Nishio, Takayuki, Morikura, Masahiro, Yamamoto, Koji, Yonetani, Ryo

“…This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent and-identically-distributed (non-IID) data in…”
Get full text

Precise Multi-Modal In-Hand Pose Estimation using Low-Precision Sensors for Robotic Assembly by von Drigalski, Felix, Hayashi, Kennosuke, Huang, Yifei, Yonetani, Ryo, Hamaya, Masashi, Tanaka, Kazutoshi, Ijiri, Yoshihisa

“…In industrial assembly tasks, the in-hand pose of grasped objects needs to be known with high precision for subsequent manipulation tasks such as insertion…”
Get full text

Prioritized Safe Interval Path Planning for Multi-Agent Pathfinding With Continuous Time on 2D Roadmaps by Kasaura, Kazumi, Nishimura, Mai, Yonetani, Ryo

“…We address a challenging multi-agent pathfinding (MAPF) problem for hundreds of agents moving on a 2D roadmap with continuous time. Despite its known potential…”
Get full text

Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption by Yonetani, Ryo, Boddeti, Vishnu Naresh, Kitani, Kris M., Sato, Yoichi

“…We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate…”
Get full text

Ego-Surfing: Person Localization in First-Person Videos Using Ego-Motion Signatures by Yonetani, Ryo, Kitani, Kris M., Sato, Yoichi

“…We envision a future time when wearable cameras are worn by the masses and recording first-person point-of-view videos of everyday life. While these cameras…”
Get full text

Adaptive Distillation for Decentralized Learning from Heterogeneous Clients by Ma, Jiaxin, Yonetani, Ryo, Iqbal, Zahid

“…This paper addresses the problem of decentralized learning to achieve a high-performance global model by asking a group of clients to share local models…”
Get full text

Discovering Objects of Joint Attention via First-Person Sensing by Kera, Hiroshi, Yonetani, Ryo, Higuchi, Keita, Sato, Yoichi

“…The goal of this work is to discover objects of joint attention, i.e., objects being viewed by multiple people using head-mounted cameras and eye trackers…”
Get full text

TSPDiffuser: Diffusion Models as Learned Samplers for Traveling Salesperson Path Planning Problems by Yonetani, Ryo

“…This paper presents TSPDiffuser, a novel data-driven path planner for traveling salesperson path planning problems (TSPPPs) in environments rich with…”
Get full text

Crowd Density Forecasting by Modeling Patch-based Dynamics by Minoura, Hiroaki, Yonetani, Ryo, Nishimura, Mai, Ushiku, Yoshitaka

“…Forecasting human activities observed in videos is a long-standing challenge in computer vision and robotics and is also beneficial for various real-world…”
Get full text

Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints by Kasaura, Kazumi, Miura, Shuwa, Kozuno, Tadashi, Yonetani, Ryo, Hoshino, Kenta, Hosoe, Yohei

“…This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the…”
Get full text

Ego-surfing first person videos by Yonetani, Ryo, Kitani, Kris M., Sato, Yoichi

“…We envision a future time when wearable cameras (e.g., small cameras in glasses or pinned on a shirt collar) are worn by the masses and record first-person…”
Get full text

Learning Robotic Contact Juggling by Tanaka, Kazutoshi, Hamaya, Masashi, Joshi, Devwrat, von Drigalski, Felix, Yonetani, Ryo, Matsubara, Takamitsu, Ijiri, Yoshihisa

“…Robotic contact juggling is a challenging task in which robots must control the movement of a ball rapidly and indirectly without holding it while keeping the…”
Get full text

CXSimulator: A User Behavior Simulation using LLM Embeddings for Web-Marketing Campaign Assessment by Kasuga, Akira, Yonetani, Ryo

“…This paper presents the Customer Experience (CX) Simulator, a novel framework designed to assess the effects of untested web-marketing campaigns through user…”
Get full text

ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives by Kitamura, Toshinori, Yonetani, Ryo

“…We present ShinRL, an open-source library specialized for the evaluation of reinforcement learning (RL) algorithms from both theoretical and practical…”
Get full text

Opt-in Camera: Person Identification in Video via UWB Localization and Its Application to Opt-in Systems by Ishige, Matthew, Yoshimura, Yasuhiro, Yonetani, Ryo

“…This paper presents opt-in camera, a concept of privacy-preserving camera systems capable of recording only specific individuals in a crowd who explicitly…”
Get full text