Yaocong Hu

Dr. Yaocong Hu


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
8 April 2024 in Multimedia Systems
Verified
Journal Article
Closed access
PDF file
YHYaocong Hu
Yaocong Hu
YLYuanyuan Lin
Yuanyuan Lin
HYHuicheng Yang
Huicheng Yang
BLBingyou Liu
Bingyou Liu
GWGuoyang Wan
Guoyang Wan
XLXiaobo Lu
Xiaobo Lu

3 September 2025 in Sensors
Verified
Journal Article
Open access
PDF file
XZXiaoyu Zhang
Xiaoyu Zhang
RCRui Cai
Rui Cai
NJNing Jiang
Ning Jiang
MXMinwen Xing
Minwen Xing
Ke XuKe Xu
Ke Xu
YHYaocong Hu
Yaocong Hu
Person re-identification aims to match images of the same individual across non-overlapping cameras by analyzing personal characteristics. Recently, Transformer-based models have demonstrated excellent capabilities and achieved breakthrough progress in this task. However, their high computational costs and inadequate capacity to capture fine-grained local features impose significant constraints on re-identification performance. To address these challenges, this paper proposes a novel Toward Efficient Transformer-based Person Re-identification (TE-TransReID) framework. Specifically, the proposed framework retains only the former L-th layer layers of a pretrained Vision Transformer (ViT) for global feature extraction while combining local features extracted from a pretrained CNN, thus achieving the trade-off between high accuracy and lightweight networks. Additionally, we propose a dual efficient feature-fusion strategy to integrate global and local features for accurate person re-identification. The Efficient Token-based Feature-Fusion Module (ETFFM) employs the gate-based network to learn fused token-wise features, while the Efficient Patch-based Feature-Fusion Module (EPFFM) utilizes a lightweight Transformer to aggregate patch-level features. Finally, TE-TransReID achieves a rank-1 of 94.8%, 88.3%, and 85.7% on Market1501, DukeMTMC, and MSMT17 with a parameter of 27.5 M, respectively. Compared to existing CNN–Transformer hybrid models, TE-TransReID maintains comparable recognition accuracy while drastically reducing model parameters, establishing an optimal equilibrium between recognition accuracy and computational efficiency.

26 June 2026 in Frontiers in Plant Science
Verified
Journal Article
Open access
PDF file
KXKe Xu
Ke Xu
DCDahui Cao
Dahui Cao
QTQinyue Tai
Qinyue Tai
HWHaiting Wang
Haiting Wang
JNJun Ni
Jun Ni
HYHuicheng Yang
Huicheng Yang
Introduction: eaf area index (LAI) and leaf nitrogen accumulation (LNA) are key indicators of wheat growth and nitrogen nutritional status. However, existing prediction methods predominantly rely on single-modal information and single-output models, limiting their ability to characterize the complex structural and physiological traits of crops. This study aimed to develop a multimodal learning framework for the simultaneous and accurate prediction of wheat LAI and LNA. Methods: Spectral, image, and canopy structural features were extracted from wheat canopies across different cultivars, nitrogen treatments, and growth stages. A canopy height correction-based preprocessing method was developed to improve the extraction of structural features. A Dual-Output Bayesian Neural Network (DO-BNN) was then constructed to simultaneously predict LAI and LNA. In addition, an Extreme Sample Mining (ESM) strategy and a joint loss function were introduced to strengthen the learning of complementary information across modalities and the intrinsic correlation between the two target variables. Results: The DO-BNN achieved its best predictive performance when all feature modalities were fused. The coefficients of determination (R²) for LAI and LNA were 0.89 and 0.77, respectively, while the corresponding relative root mean square errors (RRMSEs) were 0.15 and 0.35. Compared with single-modal and conventional single-output approaches, the proposed method provided more accurate and robust predictions of both wheat growth parameters. Discussion: The results demonstrate that integrating spectral, image, and structural information can improve the characterization of wheat canopy traits. By jointly modeling LAI and LNA, the DO-BNN effectively exploited the physiological relationship between crop growth and nitrogen accumulation. The proposed framework provides a promising approach for the high-accuracy, collaborative monitoring of wheat growth and nitrogen nutritional status.

3 December 2018 in arXiv
Verified
Preprint
Open access
PDF file
YHYaocong Hu
Yaocong Hu
MLMingQi Lu
MingQi Lu
XLXiaobo Lu
Xiaobo Lu
Abnormal driving behaviour is one of the leading cause of terrible traffic accidents endangering human life. Therefore, study on driving behaviour surveillance has become essential to traffic security and public management. In this paper, we conduct this promising research and employ a two stream CNN framework for video-based driving behaviour recognition, in which spatial stream CNN captures appearance information from still frames, whilst temporal stream CNN captures motion information with pre-computed optical flow displacement between a few adjacent video frames. We investigate different spatial-temporal fusion strategies to combine the intra frame static clues and inter frame dynamic clues for final behaviour recognition. So as to validate the effectiveness of the designed spatial-temporal deep learning based model, we create a simulated driving behaviour dataset, containing 1237 videos with 6 different driving behavior for recognition. Experiment result shows that our proposed method obtains noticeable performance improvements compared to the existing methods.