Zhe Kong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zhe Kong has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Neng Gao
Institute of Information Engineering, Chinese Academy of Sciences
2 shared publications - Yifei Zhang
Alibaba Group
2 shared publications - Yuhan Liu
Chinese Academy of Sciences
2 shared publications - Chenyang Tu
Chinese Academy of Sciences
1 shared publication - Xin Wang
Institute of Information Engineering, Chinese Academy of Sciences
1 shared publication
Latest Publications
- 22 July 2025
- Published by Springer Nature
- p. 302-316
MetaRAED: Meta Learning Prototype-Based Retrieval Augmented Few-Shot Event Detection
- 22 July 2025
- Published by Springer Nature
- p. 302-316
MetaRAED: Meta Learning Prototype-Based Retrieval Augmented Few-Shot Event Detection
- Open Access
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 310-318
Multi-level Fusion of Multi-modal Semantic Embeddings for Zero Shot Learning
Zero shot learning aims to recognize objects whose instances may not be covered by the training data. To generalize knowledge from seen classes to the novel ones, semantic space is built to embed knowledge from various views into multi-modal semantic embeddings. Existing semantic embeddings neglect the relationships between classes which are essential to transfer knowledge between classes. Moreover, existing zero shot learning models ignore the complementarity between semantic embeddings from different modalities. To tackle these problems, in this work, we resort to graph theory to explicitly model the interdependence between classes and then obtain new modal semantic embeddings. Furthermore, we pioneer to propose a multi-level fusion model to effectively combine knowledge encoded in multi-modal semantic embeddings together. By the virtue of subsequent fusion block, the results of multi-level fusion can be furtherly enriched and fused. Experiments show that our model could achieve promising results on various datasets. Ablation study suggests that our method is well suited for zero shot learning.
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 310-318
Open AccessMulti-level Fusion of Multi-modal Semantic Embeddings for Zero Shot Learning
Zero shot learning aims to recognize objects whose instances may not be covered by the training data. To generalize knowledge from seen classes to the novel ones, semantic space is built to embed knowledge from various views into multi-modal semantic embeddings. Existing semantic embeddings neglect the relationships between classes which are essential to transfer knowledge between classes. Moreover, existing zero shot learning models ignore the complementarity between semantic embeddings from different modalities. To tackle these problems, in this work, we resort to graph theory to explicitly model the interdependence between classes and then obtain new modal semantic embeddings. Furthermore, we pioneer to propose a multi-level fusion model to effectively combine knowledge encoded in multi-modal semantic embeddings together. By the virtue of subsequent fusion block, the results of multi-level fusion can be furtherly enriched and fused. Experiments show that our model could achieve promising results on various datasets. Ablation study suggests that our method is well suited for zero shot learning.