--- license: other language: - en tags: - MCE - Multimodal Learning - Imbalanced Learning --- # MCE: Towards a General Framework for Handling Missing Modalities under Imbalanced Missing Rates Published in Pattern Recognition. Modality Capability Enhancement (MCE) is a multi-modal learning framework designed to prevent performance drops when different data modalities are missing at imbalanced rates. ## Key Features Contains unimodal checkpoints (each modality), which supports: - Emotion recognition task on IEMOCAP dataset - Digit recognition task on AudiovisionMNIST dataset ## Citation If you use MCE and its checkpoints in your research, please use the following BibTeX entry. ``` @article{zhao2025mce, title={MCE: Towards a general framework for handling missing modalities under imbalanced missing rates}, author={Zhao, Binyu and Zhang, Wei and Zou, Zhaonian}, journal={Pattern Recognition}, pages={112591}, year={2025}, publisher={Elsevier} } ``` ## Links - Paper: https://doi.org/10.1016/j.patcog.2025.112591 or https://huggingface.co/papers/2510.10534 - Code: https://github.com/byzhaoAI/MCE