Jun Huang
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
Jun Huang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Shuzhen Rao
Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, People’s Republic of China
4 shared publications - Hao Pan
University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Haochang Hao
University of Illinois at Chicago, Chicago, IL, USA
2 shared publications - Huiyan Wu
Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201203, China
2 shared publications - Shuzhen Rao
Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China
2 shared publications Zengming Tang
2 shared publications
Latest Publications
- 3 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
Progressive alternating attribute-Structure optimization for multiplex heterogeneous graphs
- 3 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
Progressive alternating attribute-Structure optimization for multiplex heterogeneous graphs
- 13 January 2026
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 15 (1) , 4
Global and local label-constrained alignment for image-text matching
- 13 January 2026
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 15 (1) , 4
Global and local label-constrained alignment for image-text matching
- 15 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 654
Topology and semantic contrastive learning with joint distribution alignment for link prediction
- 15 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 654
Topology and semantic contrastive learning with joint distribution alignment for link prediction
- 20 March 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (18) , 11821-11841
Heterogeneous graph multi-level semantics extraction for node classification
- 20 March 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (18) , 11821-11841
Heterogeneous graph multi-level semantics extraction for node classification
- 28 June 2024
- Published by Elsevier in Neurocomputing
- Vol. 599
RDProtoFusion: Refined discriminative prototype-based multi-task fusion for cross-domain few-shot learning
- 28 June 2024
- Published by Elsevier in Neurocomputing
- Vol. 599
RDProtoFusion: Refined discriminative prototype-based multi-task fusion for cross-domain few-shot learning
- Open Access
Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning
In cross-domain few-shot learning, the core issue is that the model trained on source domains struggles to generalize to the target domain, especially when the domain shift is large. Motivated by the observation that the domain shift between training tasks and target tasks usually can reflect in their style variation, we propose Task Augmented Meta-Learning (TAML) to conduct style transfer-based task augmentation to improve the domain generalization ability. Firstly, Multi-task Interpolation (MTI) is introduced to fuse features from multiple tasks with different styles, which makes more diverse styles available. Furthermore, a novel task-augmentation strategy called Multi-Task Style Transfer (MTST) is proposed to perform style transfer on existing tasks to learn discriminative style-independent features. We also introduce a Feature Modulation module (FM) to add random styles and improve generalization of the model. The proposed TAML increases the diversity of styles of training tasks, and contributes to training a model with better domain generalization ability. The effectiveness is demonstrated via theoretical analysis and thorough experiments on two popular cross-domain few-shot benchmarks.
Open AccessExploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning
In cross-domain few-shot learning, the core issue is that the model trained on source domains struggles to generalize to the target domain, especially when the domain shift is large. Motivated by the observation that the domain shift between training tasks and target tasks usually can reflect in their style variation, we propose Task Augmented Meta-Learning (TAML) to conduct style transfer-based task augmentation to improve the domain generalization ability. Firstly, Multi-task Interpolation (MTI) is introduced to fuse features from multiple tasks with different styles, which makes more diverse styles available. Furthermore, a novel task-augmentation strategy called Multi-Task Style Transfer (MTST) is proposed to perform style transfer on existing tasks to learn discriminative style-independent features. We also introduce a Feature Modulation module (FM) to add random styles and improve generalization of the model. The proposed TAML increases the diversity of styles of training tasks, and contributes to training a model with better domain generalization ability. The effectiveness is demonstrated via theoretical analysis and thorough experiments on two popular cross-domain few-shot benchmarks.
- 27 January 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (15) , 10765-10778
Leveraging enhanced task embeddings for generalization in multimodal meta-learning
- 27 January 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (15) , 10765-10778
Leveraging enhanced task embeddings for generalization in multimodal meta-learning
- 23 November 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (10) , 7529-7545
Semantic-aware multi-branch interaction network for deep multimodal learning
- 23 November 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (10) , 7529-7545
Semantic-aware multi-branch interaction network for deep multimodal learning
- Open Access
- 19 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 6231
Joint Entity and Relation Extraction Network with Enhanced Explicit and Implicit Semantic Information
The main purpose of the joint entity and relation extraction is to extract entities from unstructured texts and extract the relation between labeled entities at the same time. At present, most existing joint entity and relation extraction networks ignore the utilization of explicit semantic information and explore implicit semantic information insufficiently. In this paper, we propose Joint Entity and Relation Extraction Network with Enhanced Explicit and Implicit Semantic Information (EINET). First, on the premise of using the pre-trained model, we introduce explicit semantics from Semantic Role Labeling (SRL), which contains rich semantic features about the entity types and relation of entities. Then, to enhance the implicit semantic information and extract richer features of the entity and local context, we adopt different Bi-directional Long Short-Term Memory (Bi-LSTM) networks to encode entities and local contexts, respectively. In addition, we propose to integrate global semantic information and local context length representation in relation extraction to further improve the model performance. Our model achieves competitive results on three publicly available datasets. Compared with the baseline model on Conll04, EINET obtains improvements by 2.37% in F1 for named entity recognition and 3.43% in F1 for relation extraction.
- 19 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 6231
Open AccessJoint Entity and Relation Extraction Network with Enhanced Explicit and Implicit Semantic Information
The main purpose of the joint entity and relation extraction is to extract entities from unstructured texts and extract the relation between labeled entities at the same time. At present, most existing joint entity and relation extraction networks ignore the utilization of explicit semantic information and explore implicit semantic information insufficiently. In this paper, we propose Joint Entity and Relation Extraction Network with Enhanced Explicit and Implicit Semantic Information (EINET). First, on the premise of using the pre-trained model, we introduce explicit semantics from Semantic Role Labeling (SRL), which contains rich semantic features about the entity types and relation of entities. Then, to enhance the implicit semantic information and extract richer features of the entity and local context, we adopt different Bi-directional Long Short-Term Memory (Bi-LSTM) networks to encode entities and local contexts, respectively. In addition, we propose to integrate global semantic information and local context length representation in relation extraction to further improve the model performance. Our model achieves competitive results on three publicly available datasets. Compared with the baseline model on Conll04, EINET obtains improvements by 2.37% in F1 for named entity recognition and 3.43% in F1 for relation extraction.