Publications (26)
Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensors
Lu Yin, Ziying Shi, Yinghao Wu +3
Human motion capture with sparse inertial sensors has gained significant attention recently. However, existing methods almost exclusively rely on a template adult body shape to mod…
WristSketcher: Creating Dynamic Sketches in AR with a Sensing Wristband
Enting Ying, Tianyang Xiong, Shihui Guo +3
Restricted by the limited interaction area of native AR glasses (e.g., touch bars), it is challenging to create sketches in AR glasses. Recent works have attempted to use mobile de…
Motion-R3: Fast and Accurate Motion Annotation via Representation-based Representativeness Ranking
Jubo Yu, Tianxiang Ren, Shihui Guo +6
In this paper, we follow a data-centric philosophy and propose a novel motion annotation method based on the inherent representativeness of motion data in a given dataset. Specific…
Skeleton-bridged Point Completion: From Global Inference to Local Adjustment
Yinyu Nie, Yiqun Lin, Xiaoguang Han +4
Point completion refers to complete the missing geometries of objects from partial point clouds. Existing works usually estimate the missing shape by decoding a latent feature enco…
Online Bagging for Anytime Transfer Learning
Guokun Chi, Min Jiang, Xing Gao +3
Transfer learning techniques have been widely used in the reality that it is difficult to obtain sufficient labeled data in the target domain, but a large amount of auxiliary data…
LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data
Shaocong Xu, Pengfei Li, Qianpu Sun +11
LiDAR-based semantic scene understanding is an important module in the modern autonomous driving perception stack. However, identifying outlier points in a LiDAR point cloud is cha…