A5103249600- Speech and dialogue systems
- Human Pose and Action Recognition
- 3D Surveying and Cultural Heritage
- Visual perception and processing mechanisms
- Virtual Reality Applications and Impacts
- Multimodal Machine Learning Applications
- 3D Shape Modeling and Analysis
- Interactive and Immersive Displays
- Augmented Reality Applications
- Evacuation and Crowd Dynamics
- Manufacturing Process and Optimization
Stanford University
2025
Beijing Normal University
2024
Multi-user locomotion in VR has grown increasingly common, posing numerous challenges. A key factor contributing to these challenges is the gaps experience between active and passive users during co-locomotion. Yet, there remains a limited understanding of how what extent experiential manifest diverse multi-user co-locomotion scenarios. This paper systematically explores physiological psychological indicators across various situations. Such situations include when walk, fly by joystick, or...
With the rapid development of intelligent transportation systems, traffic sign detection plays a crucial role in ensuring driving safety and preventing accidents. However, detecting small signs complex road environments remains significant challenge due to issues such as low resolution, dense distribution, visually similar background interference. Existing methods face limitations including high computational cost, inconsistent feature alignment, insufficient resolution heads. To address...
Intelligent agents need to autonomously navigate and interact within contextual environments perform a wide range of daily tasks based on human-level instructions. These require foundational understanding the world, incorporating common sense knowledge, interpret such Moreover, they must possess precise low-level skills for movement interaction execute detailed task plans derived from these In this work, we address synthesizing continuous human-object interactions manipulating large objects...
For designing a wide range of everyday objects, the design process should be aware both human body and underlying semantics specification. However, these two objectives present significant challenges to current AI-based tools. In this work, we method synthesize body-aware 3D objects from base mesh given an input geometry either text or image as guidance. The generated can simulated on virtual characters, fabricated for real-world use. We propose use deformation procedure that optimizes...