A5026643515- Gait Recognition and Analysis
- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Diabetic Foot Ulcer Assessment and Management
- Anomaly Detection Techniques and Applications
- Educational Technology and Assessment
- Distributed and Parallel Computing Systems
- Advanced Computational Techniques and Applications
- Hand Gesture Recognition Systems
- Image Enhancement Techniques
- Advanced Algorithms and Applications
- Indoor and Outdoor Localization Technologies
- Advanced Sensor and Control Systems
- Interconnection Networks and Systems
- Atrial Fibrillation Management and Outcomes
- Parallel Computing and Optimization Techniques
- Image and Signal Denoising Methods
- Network Security and Intrusion Detection
- Advanced Image and Video Retrieval Techniques
- Medical Image Segmentation Techniques
- Energy Harvesting in Wireless Networks
- E-commerce and Technology Innovations
- Energy Efficient Wireless Sensor Networks
- Advanced Measurement and Detection Methods
- Technology and Security Systems
China Earthquake Administration
2025
State Key Laboratory of Earthquake Dynamics
2025
China University of Petroleum, East China
2024-2025
Beijing University of Technology
2007-2024
Peking University
2023-2024
Wuhan Textile University
2024
China Southern Power Grid (China)
2024
Nanchang University
2024
Xinyang College of Agriculture and Forestry
2024
King Fahd University of Petroleum and Minerals
2024
Occluded person re-identification (Re-ID) focuses on addressing the occlusion problem when retrieving of interest across non-overlapping cameras. With increasing demand for intelligent video surveillance and application Re-ID technology, real-world draws considerable from researchers. Although a large number occluded methods have been proposed, there are few surveys that focus occlusion. To fill this gap help boost future research, article provides systematic survey Re-ID. In work, we review...
Gait recognition receives increasing attention since it can be conducted at a long distance in nonintrusive way and applied to the condition of changing clothes. Most existing methods take silhouettes gait sequences as input learn unified representation from multiple match probe gallery. However, these models are all faced with lack interpretability, e.g., is not clear which silhouette sequence part human body relatively more important for recognition. In this work, we propose quality aware...
Interferometric synthetic aperture radar (InSAR) technology plays a crucial role in monitoring surface deformation and has become widely used volcanic earthquake research. With the rapid advancement of satellite technology, InSAR now generates vast volumes data. Deep learning revolutionized data analysis, offering exceptional capabilities for processing large datasets. Leveraging these advancements, automatic detection from extensive datasets emerged as major research focus. In this paper,...
AMP-activated protein kinase (AMPK) is an essential sensor of cellular energy status. Defects in the α2 catalytic subunit AMPK (AMPKα1) are associated with metabolic syndrome. The current study investigated role AMPKα1 pathogenesis obesity and inflammation using male AMPKα1-deficent (AMPKα1(-/-)) mice their wild-type (WT) littermates. After being fed a high-fat diet (HFD), global AMPKα1(-/-) gained more body weight greater adiposity exhibited systemic insulin resistance dysfunction increased...
The study in the gait field has rarely paid attention to class-imbalanced learning, while realistic data always exhibits an imbalanced distribution. main reason lies difficulty of collecting cross-clothes sequences, since collection is usually aided by person re-identification and it more likely obtain sequences for a subject wearing same clothes. In this work, we formulate new problem tackle task-specific cloth-imbalanced issue, dubbed as Cloth-Imbalanced Gait Recognition, training consists...
As one enabling technique of the future sixth generation (6G) network, ultra-massive multiple- input-multiple-output (MIMO) can support high-speed data transmissions and cell coverage extension. However, it is hard to realize MIMO via traditional phased arrays due unacceptable power consumption. To address this issue, reconfigurable intelligent surface- based (RIS-based) antennas are an energy- efficient enabler since they free energy-hungry phase shifters. In article, we report performances...
High‐resolution infrared radiance spectra obtained from near nadir observations provide atmospheric, surface, and cloud property information. A fast radiative transfer model, including effects, is used for atmospheric profile parameter retrieval. The retrieval algorithm presented along with its application to recent field experiment data the NPOESS Airborne Sounder Testbed – Interferometer (NAST‐I). accuracy dependence on properties discussed. It shown that relatively accurate temperature...
Counting on-road vehicles in the highway is fundamental for intelligent transportation management. This paper presents first vehicle counting method compressed domain, aiming at achieving comparable estimation performance with pixel-domain methods. domain rather challenging due to limited information about and large variance numbers. To address this problem, we develop new low-level features mitigate challenge from insufficient videos. The proposed can be easily extracted coding-related...
Gait recognition is an emerging biometric technology for identifying pedestrians based on their unique walking patterns. In past gait recognition, global-based methods are inadequate to meet the growing demand accuracy, while commonly used part-based provided coarse and inaccurate feature representation specific body parts. Human parsing appears be a better option accurately representing complete parts in recognition. However, its practical application often hindered by missing RGB modality,...
Polarimetric SAR data has the characteristics of all-weather, all-time and so on, which is widely used in many fields. However, annotation relatively small, not conducive to our research. In this paper, we have collected five open polarimetric images, are images San Francisco area. These come from different satellites at times, great scientific research value. We annotate pixel level for image classification segmentation. For convenience researchers, annotated source...
Gait recognition aims at identifying individuals by unique walking patterns a long distance. However, prevailing methods suffer from large degradation when applied to large-scale surveillance systems. We find significant cause of this issue is that previous heavily rely on full-view person annotations reduce view differences pulling closer the anchor positive samples different viewpoints. But, subjects under in-the-wild scenarios usually have only limited number sequences As result,...
Global interests in organic foods are of importance to researchers and the food industry. Traditional questionnaire-based methods do not provide a broad picture. To meet this need, worldwide were studied by integrating query data from Google search engine deep learning methods. The results show that oil, milk, chicken, apples most interested foods; people Singapore, US, New Zealand, Australia, United Kingdom Canada care about most; consumers' interest has no correlation with GDP life...
Abstract An indium catalyzed Prins/Friedel‐Crafts tandem cyclization reaction has been developed. This provides an efficient and practical method to construct a variety of polycyclic indole frameworks with high diastereoselectivity good functional group tolerance (30 examples, up 98% yield >95 : 5 dr). The resulting products are easily accessible for further chemical transformations.
Recently the methods based on silhouettes achieve significant improvement for gait recognition. The performance, e.g., 96.4% largest OUMVLP, indicates that a promising system is around corner. However, we argue observation not true. Firstly, find there exists non-negligible gap of evaluation between academic research and practical applications. To validate assumption, conduct comprehensive study silhouette-based recognition provide new insights into limitations current methods. Our key...
Passive wireless sensors have attracted much attention due to their battery-less characteristic in the Internet of Things. However, existing passive cannot reach satisfactory sensing accuracy and transmission range as part energy from signals is used for signal processing. To address this issue, we design meta-material based on specific working principle simultaneous transmission. As a result, transceiver can detect target by analyzing reflected sensor, bypassing processing at sensor further...
Gait recognition is a soft biotechnology to identify pedestrians observed from different camera views based on specific walking patterns. However, various dressing and wearing conditions bring great challenges realistic gait recognition. Most existing methods take holistic silhouette as input focus local areas through horizontal strip division or attention map. We consider that this processing may contain mixed incomplete information about multiple body parts so misused underutilized. In...