A5114859927- EEG and Brain-Computer Interfaces
- Advanced Memory and Neural Computing
- Advanced Vision and Imaging
- Neural dynamics and brain function
- Robotics and Sensor-Based Localization
- Robot Manipulation and Learning
- Neural Networks and Applications
- Smart Grid Energy Management
- Electric Power System Optimization
- Cell Image Analysis Techniques
- Energy Load and Power Forecasting
- Neuroscience and Neural Engineering
- Image Processing Techniques and Applications
- CCD and CMOS Imaging Sensors
- Acoustic Wave Phenomena Research
- Music Technology and Sound Studies
- Visual perception and processing mechanisms
- Noise Effects and Management
- Integrated Energy Systems Optimization
- Optical measurement and interference techniques
University of Chinese Academy of Sciences
2022-2023
Wuhan University
2022-2023
Chinese Academy of Sciences
2022
Hebei University of Technology
2021
Monocular 6D pose estimation is a fundamental task in computer vision. Existing works often adopt two-stage pipeline by establishing correspondences and utilizing RANSAC algorithm to calculate 6 degrees-of-freedom (6DoF) pose. Recent try integrate differentiable algorithms achieve an end-to-end estimation. However, most of them hardly consider the geometric features 3D space, ignore topology cues when performing algorithms. To this end, we proposed Depth-Guided Edge Convolutional Network...
The visual system provides a valuable model for studying the working mechanisms of sensory processing and high-level consciousness. A significant challenge in this field is reconstruction images from decoded neural activity, which could not only test accuracy our understanding but also provide practical tool solving real-world problems. Although recent advances deep learning have improved decoding spike trains, little attention has been paid to underlying system. To address issue, we propose...
Stemming from the rapid development of artificial intelligence, which has gained expansive success in pattern recognition, robotics, and bioinformatics, neuroscience is also gaining tremendous progress. A kind spiking neural network with biological interpretability gradually receiving wide attention, this regarded as one directions toward general intelligence. This review summarizes basic properties networks well networks. Our focus on background theoretical basis neurons, different neuronal...
Monocular object 6D pose estimation is a fundamental yet challenging task in computer vision. Recently, deep learning has been proven to be capable of predicting remarkable results this task. Existing works often adopt two-stage pipeline with establishing 2D-3D correspondences and utilizing PnP/RANSAC or differentiable PnP algorithm recover 6 degrees-of-freedom (6DoF) parameters. However, most them hardly consider the geometric features 3D space, ignore topological cues when performing...
Acoustic metamaterials have exhibited wonderful engineering application prospects due to their excellent physical characteristics. Inspired by great successes of the self-similar fractal technique in design of biomimetic materials, Hilbert structure is applied to design subwavelength coiling up space acoustic metamaterial. Namely, curl propagation channel sound wave a Hilbert fractal curve. Thus, length greatly multiplied, and effective fluid particle metamaterial is ultraslow. The...
In the practical application of brain-machine interface technology, problem often faced is low information content and high noise neural signals collected by electrode difficulty decoding decoder, which makes it difficult for robotic to obtain stable instructions complete task. The idea based on principle cooperative shared control can be achieved extracting general motor commands from brain activity, while fine details movement hosted robot completion, or have control. This study proposes a...
Monocular 6D pose estimation is a fundamental task in computer vision. Existing works often adopt two-stage pipeline by establishing correspondences and utilizing RANSAC algorithm to calculate 6 degrees-of-freedom (6DoF) pose. Recent try integrate differentiable algorithms achieve an end-to-end estimation. However, most of them hardly consider the geometric features 3D space, ignore topology cues when performing algorithms. To this end, we proposed Depth-Guided Edge Convolutional Network...
Brain-computer interfaces (BCIs), is ways for electronic devices to communicate directly with the brain. For most medical-type brain-computer interface tasks, activity of multiple units neurons or local field potentials sufficient decoding. But BCIs used in neuroscience research, it important separate out individual neurons. With development large-scale silicon technology and increasing number probe channels, artificially interpreting labeling spikes becoming increasingly impractical. In...
Brain-computer interfaces (BCIs), transform neural signals in the brain into in-structions to control external devices. However, obtaining sufficient training data is difficult as well limited. With advent of advanced machine learning methods, capability brain-computer has been enhanced like never before, however, these methods require a large amount for and thus augmentation limited available. Here, we use spiking networks (SNN) generators. It touted next-generation neu-ral network...
Recently, stemming from the rapid development of artificial intelligence, which has gained expansive success in pattern recognition, robotics, and bioinformatics, neuroscience is also gaining tremendous progress. A kind spiking neural network with biological interpretability gradually receiving wide attention, this regarded as one directions toward general intelligence. This review introduces following sections, background neurons theoretical basis, different neuronal models, connectivity...
Decoding images from brain activity has been a challenge. Owing to the development of deep learning, there are available tools solve this problem. The decoded image, which aims map neural spike trains low-level visual features and high-level semantic information space. Recently, few studies decoding trains, however, these pay less attention foundations neuroscience that merged receptive field into image reconstruction. In paper, we propose learning network architecture with biological...