Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition

Yicheng Liu, Jie Wen, Chengliang Liu, Xiaozhao Fang, Zuoyong Li +2 more
2/12/2026

No official code found. Best implementation: yic20/CoMC (17 stars, MIT, last commit 2024-07-09).

Semantic Scholar

Code Implementations(1)

yic20/CoMCCommunity56%
MIT

[ICML2024] Official PyTorch implementation of CoMC: Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition

172Shell, PythonMay 28, 20242 years agoMIT

Cite this paper

@article{liu2026languagedriven,
  title  = {Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition},
  author = {Yicheng Liu and Jie Wen and Chengliang Liu and Xiaozhao Fang and Zuoyong Li and Yong Xu and Zheng Zhang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:f1b8c6487fe8286f325d3321be3c72ae6c64a03e},
  journal = {ICML 2024 2024}
}

Discussion