← Search

Haibo Li

2 accepted papers

2025

MS-RainMamba: Learning Multi-Scale State Space Models for Single Image Deraining

ICASSP 2025accepted

Despite the significant advances of Convolutional neural networks (CNNs) and Transformers in image deraining, they either suffer from limited receptive fields or incur quadratic complexity, leading to an imbalance between performance and efficiency. Recently, state space models (SSMs) have demonstra…

Cited by 0SourceScholar
2020

Key Action and Joint CTC-Attention based Sign Language Recognition

ICASSP 2020accepted

Sign Language Recognition (SLR) translates sign language video into natural language. In practice, sign language video, owning a large number of redundant frames, is necessary to be selected the essential. However, unlike common video that describes actions, sign language video is characterized as c…

Cited by 0SourceScholar