Shitao Bei — accepted AI-conference papers

2026

MoCap2GT: A High-Precision Ground Truth Estimator for SLAM Benchmarking Based on Motion Capture and IMU Fusion

Zichao Shu, Shitao Bei, Jicheng Dai, Lijun Li, Zetao Chen, Jianyu Wang

RA-L 2026

Marker-based optical motion capture (MoCap) systems are widely used to provide ground truth (GT) trajectories for benchmarking SLAM algorithms. However, the accuracy of MoCap-based GT trajectories is mainly affected by two factors: spatiotemporal calibration errors between the MoCap system and the d

Cited by 1 Source ↗Scholar ↗

2022

Up to 100x Faster Data-Free Knowledge Distillation

Gongfan Fang, Kanya Mo, Xinchao Wang, Jie Song, Shitao Bei, Haofei Zhang +1

AAAI 2022technical

Data-free knowledge distillation (DFKD) has recently been attracting increasing attention from research communities, attributed to its capability to compress a model only using synthetic data. Despite the encouraging results achieved, state-of-the-art DFKD methods still suffer from the inefficiency…

Cited by 94 Source ↗PDF ↗code ↗Scholar ↗