Hongwei Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongwei Wei has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Xiaohong Su
Harbin Institute of Technology
4 shared publications - Weining Zheng
Harbin Institute of Technology, Harbin, China
3 shared publications Wenxin Tao
3 shared publications- Cuiyun Gao
Harbin Institute of Technology, Shenzhen, China
1 shared publication - Penghong Wang
Faculty of Computing, Harbin Institute of Technology, Harbin, China
1 shared publication - Wenrui Li
Harbin Institute of Technology, Harbin, China
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13635-13649
Large Pretrained Models With Caption-Supervised Retrieval-Augmented Generation for Dense Video Captioning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13635-13649
Large Pretrained Models With Caption-Supervised Retrieval-Augmented Generation for Dense Video Captioning
- 25 September 2025
- Published by Elsevier in Computers & Security
- Vol. 159
VDExplainer: Sequential decision-making and probability sampling guided statement-level explanation for vulnerability detection
- 25 September 2025
- Published by Elsevier in Computers & Security
- Vol. 159
VDExplainer: Sequential decision-making and probability sampling guided statement-level explanation for vulnerability detection
- 22 March 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 316
Transformer-based statement level vulnerability detection by cross-modal fine-grained features capture
- 22 March 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 316
Transformer-based statement level vulnerability detection by cross-modal fine-grained features capture
- Open Access
- 21 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 32 (5) , 1-28
A Hypothesis Testing-based Framework for Software Cross-modal Retrieval in Heterogeneous Semantic Spaces
Software cross-modal retrieval is a popular yet challenging direction, such as bug localization and code search. Previous studies generally map natural language texts and codes into a homogeneous semantic space for similarity measurement. However, it is not easy to accurately capture their similar semantics in a homogeneous semantic space due to the semantic gap. Therefore, we propose to map the multi-modal data into heterogeneous semantic spaces to capture their unique semantics. Specifically, we propose a novel software cross-modal retrieval framework named Deep Hypothesis Testing (DeepHT). In DeepHT, to capture the unique semantics of the code’s control flow structure, all control flow paths (CFPs) in the control flow graph are mapped to a CFP sample set in the sample space. Meanwhile, the text is mapped to a CFP correlation distribution in the distribution space to model its correlation with different CFPs. The matching score is calculated according to how well the sample set obeys the distribution using hypothesis testing. The experimental results on two text-to-code retrieval tasks (i.e., bug localization and code search) and two code-to-text retrieval tasks (i.e., vulnerability knowledge retrieval and historical patch retrieval) show that DeepHT outperforms the baseline methods.
- 21 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 32 (5) , 1-28
Open AccessA Hypothesis Testing-based Framework for Software Cross-modal Retrieval in Heterogeneous Semantic Spaces
Software cross-modal retrieval is a popular yet challenging direction, such as bug localization and code search. Previous studies generally map natural language texts and codes into a homogeneous semantic space for similarity measurement. However, it is not easy to accurately capture their similar semantics in a homogeneous semantic space due to the semantic gap. Therefore, we propose to map the multi-modal data into heterogeneous semantic spaces to capture their unique semantics. Specifically, we propose a novel software cross-modal retrieval framework named Deep Hypothesis Testing (DeepHT). In DeepHT, to capture the unique semantics of the code’s control flow structure, all control flow paths (CFPs) in the control flow graph are mapped to a CFP sample set in the sample space. Meanwhile, the text is mapped to a CFP correlation distribution in the distribution space to model its correlation with different CFPs. The matching score is calculated according to how well the sample set obeys the distribution using hypothesis testing. The experimental results on two text-to-code retrieval tasks (i.e., bug localization and code search) and two code-to-text retrieval tasks (i.e., vulnerability knowledge retrieval and historical patch retrieval) show that DeepHT outperforms the baseline methods.