Výsledky vyhledávání - "Park, Daehee"

Report

Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning

Autor: Jeong, Jaewoo, Park, Daehee, Yoon, Kuk-Jin

Human pose forecasting garners attention for its diverse applications. However, challenges in modeling the multi-modal nature of human motion and intricate interactions among agents persist, particularly with longer timescales and more agents. In thi

Externí odkaz: http://arxiv.org/abs/2404.05218

Zobrazit plný text záznamu

Report

T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory

Autor: Park, Daehee, Jeong, Jaeseok, Yoon, Sung-Hoon, Jeong, Jaewoo, Yoon, Kuk-Jin

Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from unreliable pred

Externí odkaz: http://arxiv.org/abs/2403.10052

Zobrazit plný text záznamu

Report

Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation

Autor: Park, Daehee, Jeong, Jaewoo, Yoon, Kuk-Jin

Multi-agent trajectory prediction is crucial for various practical applications, spurring the construction of many large-scale trajectory datasets, including vehicles and pedestrians. However, discrepancies exist among datasets due to external factor

Externí odkaz: http://arxiv.org/abs/2312.15906

Zobrazit plný text záznamu

Report

Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction

Autor: Park, Daehee, Ryu, Hobin, Yang, Yunseo, Cho, Jegyeong, Kim, Jiwon, Yoon, Kuk-Jin

Understanding the interaction between multiple agents is crucial for realistic vehicle trajectory prediction. Existing methods have attempted to infer the interaction from the observed past trajectories of agents using pooling, attention, or graph-ba

Externí odkaz: http://arxiv.org/abs/2305.14715

Zobrazit plný text záznamu

Report

Sub-Chain Beam for mmWave Devices: A Trade-off between Power Saving and Beam Correspondence

Autor: Mo, Jianhua, Park, Daehee, Ng, Boon Loong, Va, Vutha, Ali, Anum, Seo, Chonghwa, Zhang, Jianzhong Charlie

Beam correspondence, or downlink-uplink (DL-UL) beam reciprocity, refers to the assumption that the best beams in the DL are also the best beams in the UL. This is an important assumption that allows the existing beam management framework in 5G to re

Externí odkaz: http://arxiv.org/abs/2112.12296

Zobrazit plný text záznamu

Report

BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning

Autor: Oh, Changgyoon, Cho, Wonjune, Park, Daehee, Chae, Yujeong, Wang, Lin, Yoon, Kuk-Jin

Providing omnidirectional depth along with RGB information is important for numerous applications, eg, VR/AR. However, as omnidirectional RGB-D data is not always available, synthesizing RGB-D panorama data from limited information of a scene can be

Externí odkaz: http://arxiv.org/abs/2112.06179

Zobrazit plný text záznamu