Align-then-generate: An effective cross-modal generation paradigm for multi-label zero-shot learning
- 4 February 2026
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 176
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (22033002)
- National Natural Science Foundation of China (62072112)
- National Natural Science Foundation of China (92370127)
- Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions
This publication has 13 references indexed in Scilit:
- Transformer-driven feature fusion network and visual feature coding for multi-label image classificationPattern Recognition, 2025
- Prototype rectification for zero-shot learningPattern Recognition, 2024
- Improving generalized zero-shot learning via cluster-based semantic disentangling representationPattern Recognition, 2024
- A Transferable Generative Framework for Multi-Label Zero-Shot LearningIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Foundation models for generalist medical artificial intelligenceNature, 2023
- Hybrid routing transformer for zero-shot learningPattern Recognition, 2022
- Feature learning network with transformer for multi-label image classificationPattern Recognition, 2022
- Zero-shot learning via a specific rank-controlled semantic autoencoderPattern Recognition, 2022
- Highly accurate protein structure prediction with AlphaFoldNature, 2021
- The Open Images Dataset V4International Journal of Computer Vision, 2020