Align-then-generate: An effective cross-modal generation paradigm for multi-label zero-shot learning

Pattern Recognition 2026

View at publisher

Authors: Peirong Ma, Wu Ran, Yanhui Gu, Huaqiu Chen, Zhiquan He, Hong Lu

DOI: 10.1016/j.patcog.2026.113229

Cited by: 0

References: 13

Fields of Study & Subjects

Domain Adaptation and Few-Shot Learning Multimodal Machine Learning Applications Advanced Neural Network Applications

References 13