Mengyu He — accepted AI-conference papers

2024

DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking

Cheng Huang, Shoudong Han, Mengyu He, Wenbo Zheng, Yuhao Wei

CVPR 2024poster

Accurate data association is crucial in reducing confusion such as ID switches and assignment errors in multi-object tracking (MOT). However existing advanced methods often overlook the diversity among trajectories and the ambiguity and conflicts present in motion and appearance cues leading to conf…

Cited by 5 Source ↗PDF ↗Scholar ↗

2021

Improving Multimodal Speech Enhancement by Incorporating Self-Supervised and Curriculum Learning

Ying Cheng, Mengyu He, Jiashuo Yu, Rui Feng

ICASSP 2021accepted

Speech enhancement in realistic scenarios still remains many challenges, such as complex background signals and data limitations. In this paper, we present a co-attention based framework that incorporates self-supervised and curriculum learning to derive the target speech in noisy environments. Spec…

Cited by 6 Source ↗Scholar ↗