Peiyu Chen — accepted AI-conference papers

2023

ESVIO: Event-Based Stereo Visual Inertial Odometry

RA-L 2023

Event cameras that asynchronously output low-latency event streams provide great opportunities for state estimation under challenging situations. Despite event-based visual odometry having been extensively studied in recent years, most of them are based on the monocular, while few research on stereo

Cited by 89 Source ↗Scholar ↗

2022

Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

Xichen Pan, Peiyu Chen, Yichen Gong, Helong Zhou, Xinbing Wang, Zhouhan Lin

ACL 2022long

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, altho…

Cited by 54 Source ↗PDF ↗code ↗Scholar ↗