Query：
学者姓名：卢孝强
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
In recent years, the rapid development of the unmanned aerial vehicle (UAV) technology has generated a large number of aerial photography images captured by UAV. Consequently, the object detection in UAV aerial images has emerged as a recent research focus. However, due to the flexible flight heights and diverse shooting angles of UAV, two significant challenges have arisen in UAV aerial images: extreme variation in target scale and the presence of numerous small targets. To address these challenges, this article introduces a semantic information-guided fusion module specifically tailored for small targets. This module utilizes high-level semantic information to guide and align the underlying texture information, thereby enhancing the semantic representation of small targets at the feature level and subsequently improving the model's ability to detect them. In addition, this article introduces a novel global-local fusion detection strategy to strengthen the detection of small targets. We have redesigned the foreground region assembly method to address the drawbacks of previous methods that involved multiple inferences. Extensive experiments conducted on the VisDrone and UAVDT datasets demonstrate that our two self-designed modules can significantly enhance the detection capability of small targets compared with the YOLOX-M model. Our code is publicly available at: https://github.com/LearnYZZ/GLSDet.
Keyword ：
Accuracy Accuracy Assembly Assembly Autonomous aerial vehicles Autonomous aerial vehicles Decoupled head attention Decoupled head attention Detectors Detectors Feature extraction Feature extraction feature fusion feature fusion Object detection Object detection remote sensing image recognition remote sensing image recognition robust adversarial robust adversarial robustness robustness rotational object detection rotational object detection Semantics Semantics Superresolution Superresolution Technological innovation Technological innovation Transformers Transformers
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Yaxiong , Ye, Zhengze , Sun, Haokai et al. Global-Local Fusion With Semantic Information Guidance for Accurate Small Object Detection in UAV Aerial Images [J]. | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2025 , 63 . |
| MLA | Chen, Yaxiong et al. "Global-Local Fusion With Semantic Information Guidance for Accurate Small Object Detection in UAV Aerial Images" . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63 (2025) . |
| APA | Chen, Yaxiong , Ye, Zhengze , Sun, Haokai , Gong, Tengfei , Xiong, Shengwu , Lu, Xiaoqiang . Global-Local Fusion With Semantic Information Guidance for Accurate Small Object Detection in UAV Aerial Images . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2025 , 63 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
在我国统筹实施科教兴国战略、人才强国战略、创新驱动发展战略,以及一体推进教育发展、科技创新、人才培养政策的引领与驱动下,高校、企业与科研院所之间的协同育人机制已经从最初的倡议和试点阶段,逐渐迈向了落地实施和深入发展时期.科教融合与产教融合协同育人模式将得到进一步的深化,主要体现在培养主体的多元化、培养层次的提升、培养机制的优化以及培养方式的创新与升级等多个方面.以福州大学物理与信息工程学院为例,针对电子信息领域国家技术和人才战略需求,探索重点高校、头部企业和科研机构通过设立定制化专班、共建科研平台、面向头部企业定向就业、共同举办学术交流论坛、共建导师团队、共同评价培养质量等方式实施研究生培养,打造全要素融合研究生培养新范式,着力实现创新型高层次人才自主培养.
Keyword ：
产教融合 产教融合 校企联合专班 校企联合专班 研究生培养 研究生培养 科教融合 科教融合
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 杨晓丹 , 柯颖莹 , 郑志刚 et al. 全要素融合的研究生产学研协同培养机制构建研究 [J]. | 中国高校科技 , 2025 , (2) : 93-96 . |
| MLA | 杨晓丹 et al. "全要素融合的研究生产学研协同培养机制构建研究" . | 中国高校科技 2 (2025) : 93-96 . |
| APA | 杨晓丹 , 柯颖莹 , 郑志刚 , 魏金明 , 卢孝强 , 李福山 . 全要素融合的研究生产学研协同培养机制构建研究 . | 中国高校科技 , 2025 , (2) , 93-96 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Solar-blind ultraviolet photodetectors (SBUV-PDs) are utilized in various military and civilian fields, encompassing missile tracking, high-voltage detection, and fire warning systems. Ga2O3 emerges as the prime candidate for such PDs owing to its elevated bandgap, remarkable thermal stability, and facile fabrication process. The metal-semiconductor-metal (MSM) structure garners attention for its swift response time and straightforward preparation, thus becoming a focal point among diverse PD architectures. Nevertheless, the metal surface impedes optical absorption, thereby diminishing the quantum efficiency of the PD. In this work, we introduce a nanograting onto the Ga2O3 surface, which results in a 747-fold increase in responsivity in the SBUV region compared to a normal MSM grating-free structure. Metal gratings can induce surface plasmon polaritons (SPP), thereby augmenting the optical absorption of the PD and stimulating hot electrons to increase photocurrent. However, the broadband response caused by the introduction of metal gratings is a common problem. By optimizing the doping concentration of the Ga2O3 absorption layer, adjusting the incident light intensity, and reverse voltage, the problem of broadband response has been solved. The responsivity of the device in the non-SBUV region is suppressed 24-fold. This methodology holds promise as a reliable approach for fabricating high-performance SBUV-PDs.
Keyword ：
Ga2O3 Ga2O3 metal-semiconductor-metal (MSM) metal-semiconductor-metal (MSM) nanograting nanograting photodetector (PD) photodetector (PD) plasmon plasmon responsivity responsivity
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Jialong , Yang, Dan , Lu, Xiaoqiang et al. Enhancing Ga2O3 Solar-Blind Photodetectors via Metal Nanogratings [J]. | IEEE SENSORS JOURNAL , 2025 , 25 (1) : 434-442 . |
| MLA | Li, Jialong et al. "Enhancing Ga2O3 Solar-Blind Photodetectors via Metal Nanogratings" . | IEEE SENSORS JOURNAL 25 . 1 (2025) : 434-442 . |
| APA | Li, Jialong , Yang, Dan , Lu, Xiaoqiang , Zhang, Haizhong , Zhu, Minmin . Enhancing Ga2O3 Solar-Blind Photodetectors via Metal Nanogratings . | IEEE SENSORS JOURNAL , 2025 , 25 (1) , 434-442 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Mobile edge caching (MEC) has grown substantially with the rapid development in scale and complexity of data traffic. By exploiting the expansive coverage of autonomous aerial vehicles (AAVs), MEC enables services for massive vehicle users (VUs) simultaneously, which is promising for enhancing network transmission efficiency. Nonetheless, due to challenges arising from the timeliness and freshness of content services caused by AAVs' limited endurance and airborne capacity, caching strategy considering the real-time of content in large-scale dynamic Internet of Vehicles (IoV) environments remains open. With the above consideration, in this article, the cache refreshing cycle and content placement are jointly optimized in the cache-enabled AAV-assisted vehicular integrated networks (CAVINs) to minimize the content Age of Information (AoI) and energy consumption of the macro AAV. Since the joint optimization problem is variational coupled with nonconvex binary constraints, it is decoupled and solved by a double-iteration method. Specifically, the optimal cache refreshing cycle is derived in semi-closed form with the Karush-Kuhn-Tucker (KKT) conditions. The locally optimal solution of the content placement is obtained through successive convex approximation (SCA). Simulation results corroborate the effectiveness and superiority of the proposed scheme.
Keyword ：
Age of Information (AoI) Age of Information (AoI) Autonomous aerial vehicles Autonomous aerial vehicles Complexity theory Complexity theory Energy consumption Energy consumption Energy efficiency Energy efficiency Information age Information age Internet of Vehicles Internet of Vehicles Internet of Vehicles (IoV) Internet of Vehicles (IoV) mobile edge caching (MEC) mobile edge caching (MEC) Optimization Optimization Real-time systems Real-time systems Simulation Simulation unmanned aerial vehicles (AAVs)-assisted networks unmanned aerial vehicles (AAVs)-assisted networks Vehicle dynamics Vehicle dynamics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiao, Yang , Lin, Zhijian , Cao, Xiaoxiao et al. AoI Energy-Efficient Edge Caching in AAV-Assisted Vehicular Networks [J]. | IEEE INTERNET OF THINGS JOURNAL , 2025 , 12 (6) : 6764-6774 . |
| MLA | Xiao, Yang et al. "AoI Energy-Efficient Edge Caching in AAV-Assisted Vehicular Networks" . | IEEE INTERNET OF THINGS JOURNAL 12 . 6 (2025) : 6764-6774 . |
| APA | Xiao, Yang , Lin, Zhijian , Cao, Xiaoxiao , Chen, Youjia , Lu, Xiaoqiang . AoI Energy-Efficient Edge Caching in AAV-Assisted Vehicular Networks . | IEEE INTERNET OF THINGS JOURNAL , 2025 , 12 (6) , 6764-6774 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In hyperspectral images (HSIs), different land cover (LC) classes have distinct reflective characteristics at various wavelengths. Therefore, relying on only a few bands to distinguish all LC classes often leads to information loss, resulting in poor average accuracy. To address this problem, we propose a method called Cascaded Spatial Cross-Attention Network (CSCANet) for HSI classification. We design a cascaded spatial cross-attention module, which first performs cross-attention on local and global features in the spatial context, then uses a group cascade structure to sequentially propagate important spatial regions within the different channels, and finally obtains joint attention features to improve the robustness of the network. Moreover, we also design a two-branch feature separation structure based on spatial-spectral features to separate different LC Tokens as much as possible, thereby improving the distinguishability of different LC classes. Extensive experiments demonstrate that our method achieves excellent performance in enhancing classification accuracy and robustness.
Keyword ：
Accuracy Accuracy Artificial intelligence Artificial intelligence Data mining Data mining Feature extraction Feature extraction group cascade structure group cascade structure Hyperspectral image classification Hyperspectral image classification Hyperspectral imaging Hyperspectral imaging Image classification Image classification Reflectivity Reflectivity spatial cross-attention spatial cross-attention spatial-spectral feature extraction spatial-spectral feature extraction Sun Sun Technological innovation Technological innovation Transformers Transformers
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Bo , Chen, Yaxiong , Xiong, Shengwu et al. Hyperspectral Image Classification via Cascaded Spatial Cross-Attention Network [J]. | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2025 , 34 : 899-913 . |
| MLA | Zhang, Bo et al. "Hyperspectral Image Classification via Cascaded Spatial Cross-Attention Network" . | IEEE TRANSACTIONS ON IMAGE PROCESSING 34 (2025) : 899-913 . |
| APA | Zhang, Bo , Chen, Yaxiong , Xiong, Shengwu , Lu, Xiaoqiang . Hyperspectral Image Classification via Cascaded Spatial Cross-Attention Network . | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2025 , 34 , 899-913 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Lensless imaging has gained popularity in various applications due to its userfriendly nature, cost-effectiveness, and compact design. However, achieving high-quality image reconstruction within this framework remains a significant challenge. Lensless imaging measurements are associated with distinct point spread functions (PSFs), resulting in many PSFs introducing artifacts into the underlying physical model. This discrepancy between the actual and prior models poses challenges for standard reconstruction methods to effectively address high-quality image reconstruction by solving a regularization-based inverse problem. To overcome these issues, we propose MN-FISTA-Net, an unrolled neural network that unfolds the fast iterative shrinkage/thresholding algorithm for solving mixed norm regularization with a deep denoiser prior. Our method enhances mask-based lensless imaging performance by efficiently addressing noise and model mismatch, as evidenced by significant improvements in image quality compared to existing approaches. © 2024 Optica Publishing Group.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Qian, H. , Ling, H. , Lu, X. . Robust unrolled network for lensless imaging with enhanced resistance to model mismatch and noise [J]. | Optics Express , 2024 , 32 (17) : 30267-30283 . |
| MLA | Qian, H. et al. "Robust unrolled network for lensless imaging with enhanced resistance to model mismatch and noise" . | Optics Express 32 . 17 (2024) : 30267-30283 . |
| APA | Qian, H. , Ling, H. , Lu, X. . Robust unrolled network for lensless imaging with enhanced resistance to model mismatch and noise . | Optics Express , 2024 , 32 (17) , 30267-30283 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this Letter, a Ga2O3 vertical Schottky barrier diode (SBD) with self-aligned field plate and mesa termination is fabricated and studied. The combination of field plate and mesa termination can effectively make the electric field distribution uniform in the termination, and thus the proposed SBD features high breakdown voltage (BV). Moreover, to eliminate alignment deviation and simplify the fabrication process, a self-aligned etching process is developed. The experimental results show that a low specific on-resistance of 4.405 mΩ·cm2 and a high BV of 3113 V can be simultaneously derived on the proposed SBD, yielding a high power figure of merit of 2.2 GW/cm2. Meanwhile, a considerably low forward voltage of 1.53 V at 100 A/cm2 is also achieved, demonstrating the low conduction loss of the device. © 2024 Author(s).
Keyword ：
Electric fields Electric fields Etching Etching Gallium compounds Gallium compounds Schottky barrier diodes Schottky barrier diodes
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Xiaorui , Deng, Yicong , Li, Titao et al. Over 2 GW/cm2 low-conduction loss Ga2O3 vertical SBD with self-aligned field plate and mesa termination [J]. | Applied Physics Letters , 2024 , 125 (2) . |
| MLA | Xu, Xiaorui et al. "Over 2 GW/cm2 low-conduction loss Ga2O3 vertical SBD with self-aligned field plate and mesa termination" . | Applied Physics Letters 125 . 2 (2024) . |
| APA | Xu, Xiaorui , Deng, Yicong , Li, Titao , Chen, Duanyang , Wang, Fangzhou , Yu, Cheng et al. Over 2 GW/cm2 low-conduction loss Ga2O3 vertical SBD with self-aligned field plate and mesa termination . | Applied Physics Letters , 2024 , 125 (2) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Significant advancements in artificial neural networks (ANNs) have driven the rapid progress of artificial intelligence and machine learning. While current feedforward neural networks primarily handle static data, recurrent neural networks (RNNs) are designed for dynamical systems. However, RNNs demand extensive training on specific tasks, limiting their scalability and affordability for edge computing. Physical reservoir computing (RC) offers an alternative approach by mapping inputs into high-dimensional states, allowing for pattern analysis within a fixed reservoir. Unlike RNNs, RC is well-suited for temporal and sequential data processing with rapid speed and low training costs. This makes RC suitable for hardware implementation across various research domains. Nonetheless, existing demonstrations of RC remain constrained to small-scale device arrays. As electronic synapse arrays aim to approach very large-scale and highly complex hardware as in the human brain, managing heat dissipation becomes a formidable challenge. In this work, we successfully developed the neuristors based on textured h-BN films, prepared using a CMOS-compatible technique, and constructed a physical RC system based on as-fabricated devices. Our approach leverages vertically aligned BN to provide aligned diffusion paths for the reproducible migration process of metal ions from the electrodes and offers a potential solution for thermal management in electronic devices. This achievement highlights the promising potential of our neuristors for future high-density and energy-efficient neuromorphic computing. © 2024 Elsevier B.V.
Keyword ：
Boron nitride Boron nitride Highly textured Highly textured High thermal conductivity High thermal conductivity Neuromorphic device Neuromorphic device Reservoir computing Reservoir computing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, H. , Li, J. , Ju, X. et al. Highly textured CMOS-compatible hexagonal boron nitride-based neuristor for reservoir computing [J]. | Chemical Engineering Journal , 2024 , 498 . |
| MLA | Zhang, H. et al. "Highly textured CMOS-compatible hexagonal boron nitride-based neuristor for reservoir computing" . | Chemical Engineering Journal 498 (2024) . |
| APA | Zhang, H. , Li, J. , Ju, X. , Jiang, J. , Wu, J. , Chi, D. et al. Highly textured CMOS-compatible hexagonal boron nitride-based neuristor for reservoir computing . | Chemical Engineering Journal , 2024 , 498 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Mobile edge caching (MEC) has grown substantially with the rapid development in scale and complexity of data traffic. By exploiting the expansive coverage of unmanned aerial vehicles (UAVs), MEC enables services for massive vehicle users (VUs) simultaneously, which is promising for enhancing network transmission efficiency. Nonetheless, due to challenges arising from the timeliness and freshness of content services caused by UAVs' limited endurance and airborne capacity, caching strategy considering the real-time of content in large-scale dynamic Internet of Vehicles (IoV) environments remains open. With the above consideration, in this paper, the cache refreshing cycle and content placement are jointly optimized in the cache-enabled UAV-assisted vehicular integrated networks (CUVIN) to minimize the content age of information (AoI) and energy consumption of the macro UAV. Since the joint optimization problem is variational coupled with non-convex binary constraints, it is decoupled and solved by a double-iteration method. Specifically, the optimal cache refreshing cycle is derived in semi-closed form with the Karush-Kuhn-Tucker (KKT) conditions. The locally optimal solution of the content placement is obtained through successive convex approximation (SCA). Simulation results corroborate the effectiveness and superiority of the proposed scheme. © 2024 IEEE.
Keyword ：
Age of information (AoI) Age of information (AoI) internet of vehicles (IoV) internet of vehicles (IoV) mobile edge caching (MEC) mobile edge caching (MEC) unmanned aerial vehicles (UAV)-assisted networks unmanned aerial vehicles (UAV)-assisted networks
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiao, Y. , Lin, Z. , Cao, X. et al. AoI-Energy-Efficient Edge Caching in UAV-Assisted Vehicular Networks [J]. | IEEE Internet of Things Journal , 2024 . |
| MLA | Xiao, Y. et al. "AoI-Energy-Efficient Edge Caching in UAV-Assisted Vehicular Networks" . | IEEE Internet of Things Journal (2024) . |
| APA | Xiao, Y. , Lin, Z. , Cao, X. , Chen, Y. , Lu, X. . AoI-Energy-Efficient Edge Caching in UAV-Assisted Vehicular Networks . | IEEE Internet of Things Journal , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, weakly supervised temporal sentence grounding in videos (TSGV) has attracted extensive attention because it does not require precise start-end time annotations during training, and it can quickly retrieve interesting segments according to user needs. In weakly supervised TSGV, query reconstruction (QR)-based methods are the current mainstream, and the quality of proposals determines their performance. QR-based methods have two problems in proposal quality. First, a multi-modal global token is usually mapped to proposals with limited duration diversity, making it difficult to capture relevant segments at varying durations in real scenarios. Additionally, Gaussian functions are typically used to generate relatively fixed weights for frames within proposals, which weigh the original video features to generate proposal-specific features. This results in query-irrelevant frames affecting the discrimination of the proposal features. In this study, we propose a query-aware multi-scale proposal network (QMN). Initially, pre-trained encoders are used to extract video and query features. Subsequently, a multi-scale proposal generation module is designed to refine video features guided by queries and diversify the duration of the proposal. This module performs multi-modal interaction and multi-scale modeling to obtain proposals of different durations. Furthermore, to extract discriminative proposal features and enhance the modeling of proposal frame correlation, a query-aware weight generator is constructed to learn frame weights to suppress query-irrelevant frame representations through contrastive learning. Finally, the masked query is reconstructed using the proposal features to select the best proposal. The effectiveness of the proposed QMN is verified through experiments on the Charades-STA and ActivityNet-Captions datasets. © 2024 Elsevier B.V.
Keyword ：
Contrastive Learning Contrastive Learning Self-supervised learning Self-supervised learning Structured Query Language Structured Query Language Supervised learning Supervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhou, Mingyao , Chen, Wenjing , Sun, Hao et al. Query-aware multi-scale proposal network for weakly supervised temporal sentence grounding in videos [J]. | Knowledge-Based Systems , 2024 , 304 . |
| MLA | Zhou, Mingyao et al. "Query-aware multi-scale proposal network for weakly supervised temporal sentence grounding in videos" . | Knowledge-Based Systems 304 (2024) . |
| APA | Zhou, Mingyao , Chen, Wenjing , Sun, Hao , Xie, Wei , Dong, Ming , Lu, Xiaoqiang . Query-aware multi-scale proposal network for weakly supervised temporal sentence grounding in videos . | Knowledge-Based Systems , 2024 , 304 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
