Wenchao Yu

Wenchao Yu

Auto-generated profile, based on publicly available information

Wenchao Yu

State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University , Chongqing 400044, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
22 June 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
FHFushuo Huo
Fushuo Huo
XZXuegui Zhu
Xuegui Zhu
QZQian Zhang
Qian Zhang
ZLZiming Liu
Ziming Liu
WYWenchao Yu
Wenchao Yu
Salient object detection (SOD) has been widely used in practical applications, such as multisensor image fusion, remote sensing, and defect detection. Recently, SOD from RGB and thermal (T) has been rapidly developed due to its robustness to extreme situations, such as low illumination and occlusion. However, existing methods all utilize a dual-stream encoder, which significantly increases the computation burdens and hinders real-world deployment. To this end, we propose a real-time One-stream Semantic-guided Refinement Network (OSRNet) for RGB-T SOD. Specifically, we first fuse the RGB and T via concatenation, addition, and multiplication operations to dig the complementary information between each modality. The efficient early fusion not only facilitates the information exchange between each modality but also avoids the cumbersome dual-stream encoder structure. Then, the lightweight decoder is proposed, making the high-level semantic information filter the low-level noisy features and gradually refine the final prediction. Also, we apply deep supervision to make the training procedure more stable and fast. Due to the early fusion strategy, OSRNet can run at a real-time speed (53–60 fps) on a single GPU. Extensive quantitative and qualitative experiments show that our network outperforms 11 state-of-the-art methods in terms of seven evaluation metrics. Our codes have been released at https://github.com/huofushuo/OSRNet .

1 March 2024 in AIP Advances
Verified
Journal Article
Open access
PDF file
XZXuegui Zhu
Xuegui Zhu
WYWenchao Yu
Wenchao Yu
GLGengjian Liu
Gengjian Liu
CZChenxing Zhang
Chenxing Zhang
Aiming at the energy supply problem of underwater equipment such as manned deep submarines, submarine base stations, etc., this paper proposes an underwater high-energy laser wireless power transmission system and focuses on analyzing the influence of the steady-state thermal blooming effect on the quality of underwater high-energy laser power transmission. First, the intensity distributions under the influence of the thermal blooming effect are numerically simulated based on the multiple phase-screen method and the fast Fourier transform, considering the changes in the initial beam radius, transmission distance, transmitting power, wavelength, absorption coefficient of the water medium, and isobaric specific heat capacity. Emphatically, transmission efficiency and beam flux contrast are used to characterize the quality of power transmission and then find the suitable laser modes and seawater environment for underwater power transmission. The results indicate that reducing the thermal blooming effect may increase the efficiency of light energy transmission, but it will also decrease the photoelectric conversion efficiency of photovoltaic cells. Therefore, for balancing the energy transfer efficiency and the beam flux contrast, it is necessary to choose appropriate initial laser parameters based on actual underwater environmental parameters. Our study is helpful for the design of the underwater laser wireless power transmission system.

15 March 2021 in arXiv
Verified
Preprint
Open access
PDF file
JHJunheng Hao
Junheng Hao
MCMuhao Chen
Muhao Chen
WYWenchao Yu
Wenchao Yu
YSYizhou Sun
Yizhou Sun
WWWei Wang
Wei Wang
Many large-scale knowledge bases simultaneously represent two views of knowledge graphs (KGs): an ontology view for abstract and commonsense concepts, and an instance view for specific entities that are instantiated from ontological concepts. Existing KG embedding models, however, merely focus on representing one of the two views alone. In this paper, we propose a novel two-view KG embedding model, JOIE, with the goal to produce better knowledge embedding and enable new applications that rely on multi-view knowledge. JOIE employs both cross-view and intra-view modeling that learn on multiple facets of the knowledge base. The cross-view association model is learned to bridge the embeddings of ontological concepts and their corresponding instance-view entities. The intra-view models are trained to capture the structured knowledge of instance and ontology views in separate embedding spaces, with a hierarchy-aware encoding technique enabled for ontologies with hierarchies. We explore multiple representation techniques for the two model components and investigate with nine variants of JOIE. Our model is trained on large-scale knowledge bases that consist of massive instances and their corresponding ontological concepts connected via a (small) set of cross-view links. Experimental results on public datasets show that the best variant of JOIE significantly outperforms previous models on instance-view triple prediction task as well as ontology population on ontologyview KG. In addition, our model successfully extends the use of KG embeddings to entity typing with promising performance.