A5100750079- Multimodal Machine Learning Applications
- Advanced Battery Technologies Research
- Advanced Sensor and Energy Harvesting Materials
- Advanced Graph Theory Research
- Advanced Algorithms and Applications
- Phase Change Materials Research
- Electric and Hybrid Vehicle Technologies
- Robot Manipulation and Learning
- Tactile and Sensory Interactions
- Opportunistic and Delay-Tolerant Networks
- Advanced Battery Materials and Technologies
- Domain Adaptation and Few-Shot Learning
- Mobile Ad Hoc Networks
- Graph theory and applications
- graph theory and CDMA systems
- Fullerene Chemistry and Applications
- Advanced Optical Sensing Technologies
- Hormonal and reproductive studies
- Sports Dynamics and Biomechanics
- Human Pose and Action Recognition
- Robotic Locomotion and Control
- Dam Engineering and Safety
- Cooperative Communication and Network Coding
- Advanced Vision and Imaging
- Icing and De-icing Technologies
Zhongyuan University of Technology
2023-2025
Second Affiliated Hospital of Zhejiang University
2024
Cixian People's Hospital
2024
OriginWater (China)
2023
Kuaishou (China)
2023
Carnegie Mellon University
2023
Fujian Institute of Oceanography
2023
Ministry of Natural Resources
2023
Lawrence Livermore National Laboratory
2022
Georgia Institute of Technology
2020
Abstract Thermoplastic glass fiber composites exhibit the advantageous characteristic of easy recyclability for both fibers and resin, which is beneficial to address challenges associated with recycling difficulties environmental pollution stemming from traditional thermosetting composite materials. This paper proposes first time preparation PMMA thermoplastic resin/glass (GF) + polyethylene terephthalate (PET) foam sandwich panels using a vacuum infusion process mixed resin polymethyl...
Illustrating a multi-sentence story with visual content is significant challenge in multimedia research. While previous works have focused on sequential story-to-visual representations at the image level or representing single sentence video clip, illustrating long coherent videos remains an under-explored area. In this paper, we propose task of video-based illustration that focuses goal visually retrieved clips. To support task, first create large-scale dataset stories each sample,...
Panoptic Scene Graph (PSG) generation aims to generate scene graph representations based on panoptic segmentation instead of rigid bounding boxes. Existing PSG methods utilize one-stage paradigm which simultaneously generates graphs and predicts semantic masks or two-stage that first adopt an off-the-shelf segmentor, then pairwise relationship prediction between these predicted objects. One-stage approach despite having a simplified training paradigm, its results are usually...
Abstract Background Previous observational studies have indicated an inverse correlation between circulating sex hormone binding globulin (SHBG) levels and the incidence of polycystic ovary syndrome (PCOS). Nevertheless, conventional may be susceptible to bias. Consequently, we conducted a two-sample Mendelian randomization (MR) investigation delve deeper into connection SHBG risk PCOS. Methods We employed single-nucleotide polymorphisms (SNPs) linked serum as instrumental variables (IVs)....
Dynamic legged locomotion is being explored as a means to maneuver on rugged and unstructured terrains. However, limited foot contact sensing capabilities often prohibit bipedal robots from deployed complex Locomotion over cluttered outdoor environments requires the contacting be aware of terrain geometries, stiffness, granular media properties. To achieve this, we designed new soft pad integrated with variety embedded sensors, including tactile, acoustic, capacitive, temperature well an...
Video-text retrieval is a class of cross-modal representation learning problems, where the goal to select video which corresponds text query between given and pool candidate videos. The contrastive paradigm vision-language pretraining has shown promising success with large-scale datasets unified transformer architecture, demonstrated power joint latent space. Despite this, intrinsic divergence visual domain textual still far from being eliminated, projecting different modalities into space...
Solid particles, such as rice and coffee beans, are commonly stored in containers ubiquitous our daily lives. Understanding those particles' properties could help us make later decisions or perform manipulation tasks pouring. Humans typically interact with the to get an understanding of particles inside them, but it is still a challenge for robots achieve that. This work utilizes tactile sensing estimate multiple solid enclosed container, specifically, content mass, volume, particle size,...
Network processors employ a multithreaded, chip-multiprocessing architecture to effectively hide memory latency and deliver high performance for packet processing applications. In such parallel paradigm, when multiple threads modify shared variable in the external memory, should be properly synchronized that accesses are protected by critical sections. Therefore, order efficiently harness potential of network processors, it is synchronization multi-threading multiprocessing. this paper, we...
The controllable synthesis of iron oxides particles is a critical issue for materials science, energy storage, biomedical applications, environmental and earth science. However, with desired phase size are still time-consuming trial-and-error process. This study presents solutions two fundamental challenges in synthesis: predicting the outcome from specified reaction parameters correlating sets to obtain products outcomes. Four machine learning algorithms, including random forest, logistic...
Solid particles, such as rice and coffee beans, are commonly stored in containers ubiquitous our daily lives. Understanding those particles' properties could help us make later decisions or perform manipulation tasks pouring. Humans typically interact with the to get an understanding of particles inside them, but it is still a challenge for robots achieve that. This work utilizes tactile sensing estimate multiple solid enclosed container, specifically, content mass, volume, particle size,...