Shuhuai Wang

Shuhuai Wang

Auto-generated profile, based on publicly available information

Shuhuai Wang

School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 March 2023 in IEEE Access
Verified
Journal Article
Open access
XJXu junhao
Xu junhao
ZLZheng Liu
Zheng Liu
XPXinlei Pei
Xinlei Pei
SWShuhuai Wang
Shuhuai Wang
SGShanshan Gao
Shanshan Gao
As a fundamental branch in cross-modal retrieval, image-text retrieval is still a challenging problem largely due to the complementary and imbalanced relationship between different modalities. However, existing works have not effectively scanned and aligned the semantic units distributed in different granularities of images and texts. To address these issues, we propose a dual-branch foreground-background fusion network (FB-Net), which is implemented by fully exploring and fusing the complementarity in semantic units collected from the foreground and background areas of instances (e.g., images and texts). Firstly, to generate multi-granularity semantic units from images and texts, multi-scale semantic scanning is conducted on both foreground and background areas through multi-level overlapped sliding windows. Secondly, to align semantic units between images and texts, the stacked cross-attention mechanism is used to calculate the initial image-text similarity. Thirdly, to further adaptively optimize the image-text similarity, the dynamically self-adaptive weighted loss is designed. Finally, to perform the image-text retrieval, the similarities between multi-granularity foreground and background semantic units are fused to obtain the final image-text similarity. Experimental results show that our proposed FB-Net outperforms representative state-of-the-art methods for image-text retrieval, and ablation studies further verify the effectiveness of each component in FB-Net.

1 January 2026 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
DCDuo Chai
Duo Chai
ZLZizhen Liu
Zizhen Liu
SWShuhuai Wang
Shuhuai Wang
SPSongwei Pei
Songwei Pei
CLCheng Liu
Cheng Liu
SWShangguang Wang
Shangguang Wang

27 October 2025
Verified
Conference Paper
Open access
BLBingfeng Liu
Bingfeng Liu
SPSongwei Pei
Songwei Pei
SWShuhuai Wang
Shuhuai Wang
WYWenzheng Yang
Wenzheng Yang
QLQian Li
Qian Li
SWShangguang Wang
Shangguang Wang

9 November 2026
Verified
Conference Paper
Open access
BLBingfeng Liu
Bingfeng Liu
SPSongwei Pei
Songwei Pei
SWShuhuai Wang
Shuhuai Wang
YHYuanzhou Huang
Yuanzhou Huang
YWYifei Wu
Yifei Wu
SWShangguang Wang
Shangguang Wang

1 January 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
YHYuanzhou Huang
Yuanzhou Huang
SPSongwei Pei
Songwei Pei
RZRui Zeng
Rui Zeng
SWShuhuai Wang
Shuhuai Wang
BLBingfeng Liu
Bingfeng Liu
SWShangguang Wang
Shangguang Wang

25 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
SWShuhuai Wang
Shuhuai Wang
ZLZheng Liu
Zheng Liu
XPXinlei Pei
Xinlei Pei
XJXu junhao
Xu junhao
Image-text retrieval aims to search related results of one modality by querying another modality. As a fundamental and key problem in cross-modal retrieval, image-text retrieval is still a challenging problem owing to the complementary and imbalanced relationship between different modalities (i.e., Image and Text) and different granularities (i.e., Global-level and Local-level). However, existing works have not fully considered how to effectively mine and fuse the complementarities between images and texts at different granularities. Therefore, in this paper, we propose a hierarchical adaptive alignment network, whose contributions are as follows: (1) We propose a multi-level alignment network, which simultaneously mines global-level and local-level data, thereby enhancing the semantic association between images and texts. (2) We propose an adaptive weighted loss to flexibly optimize the image-text similarity with two stages in a unified framework. (3) We conduct extensive experiments on three public benchmark datasets (Corel 5K, Pascal Sentence, and Wiki) and compare them with eleven state-of-the-art methods. The experimental results thoroughly verify the effectiveness of our proposed method.