Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks57 from public data
- 119
- High-Resolution Depth Maps Imaging via Attention-Based Hierarchical Multi-Modal Fusion79
To effectively extract and combine relevant information from LR depth and HR guidance, a multi-modal attention based fusion (MMAF) strategy for hierarchical convolutional layers, including a feature enhancement block to select valuable features and a feature recalibration block to unify the similarity metrics of modalities with different appearance characteristics are proposed.
- Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation72
This paper proposes a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously, and defines two implicit neural functions to estimate projection direction and distance respectively, which can be trained by two pretext learning tasks.
- Guided Depth Map Super-Resolution: A Survey71
A comprehensive survey of recent progress in guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution depth map from a low-resolution observation with the help of a paired high- resolution color image, is presented.
- 67
- Deep Attentional Guided Image Filtering63
This work proposes an attentional kernel learning module to generate dual sets of filter kernels from the guidance and the target and then adaptively combine them by modeling the pixelwise dependency between the two images.
- 63
- 49
- Targeting pro-inflammatory T cells as a novel therapeutic approach to potentially resolve atherosclerosis in humans45
T cell-targeting immunotherapy can be an effective strategy to resolve AS in humans, and this work suggests that T cell-targeting immunotherapy can be an effective strategy to resolve AS in humans.
- 37
- 36
- 22
- 20
- 18
- 17
- 17
- 17
- Super-Resolving Face Image by Facial Parsing Information16
A novel parsing map guided face super-resolution network which extracts the face prior directly from low-resolution face image for the following utilization and develops a multi-scale refine block to maintain spatial and contextual information and take advantage of multi- scale features to refine the feature representations.
- 16
- 15
- 15
- 15
- Pruning filters with L1-norm and standard deviation for CNN compression13
A new method to judge the importance of filters that uses the standard deviation to represent the amount of information extracted by the filter and can reduce inference cost by up to 50% for VGG16 and 35% for ResNet18/34 on CIFAR10 with little accuracy loss.
- Autonomous landing of a helicopter UAV with a ground-based multisensory fusion system12
This paper proposed a multisensory fusion to autonomous landing of an UAV, which includes an infrared camera, an Ultra-wideband radar that measure distance between UAV and Ground-Based system, an PAN-Tilt Unit (PTU) and an ultra- wideband radar distance module.
- 10
- 9
- 9
- Big Data-Based Early Fault Warning of Batteries Combining Short-Text Mining and Grey Correlation9
A novel data-driven method by the fusion of the short-text mining and the grey correlation for early-stage battery-fault warning that can effectively predict the faults and carry out the desired early fault warning is proposed.
- Design of PSD based solar direction sensor7
A measuring sensor based on Position Sensitive Detectors, installed at the bottom of the canister which has a narrow light pinhole so that light could pass through it, can run stably and can work as designed.
- 6
- A novel adaptive cubic quasi‐Newton optimizer for deep learning based medical image analysis tasks, validated on detection of COVID‐19 and segmentation for COVID‐19 lung infection, liver tumor, and optic disc/cup5
The purpose is to design an adaptive cubic quasi‐Newton optimizer, which could help to escape from suboptimal solution and improve the performance of deep neural networks on four medical image analysis tasks including: detection of COVID‐19, CO VID‐19 lung infection segmentation, liver tumor segmentsation, optic disc/cup segmentation.
- Hyperspectral Image Super-Resolution Using Multi-scale Feature Pyramid Network5
A novel DL-based model for single HS image super-resolution in which a feature pyramid block is designed to extract multi-scale features of the input HS image, which outperforms state-of-the-arts on both objective quality indices and subjective visual results.
- A fast calibration method for autonomous landing of UAV with ground-based multisensory fusion system5
- 4
- A comparative study of recently deep learning optimizers4
This article makes a review of some popular historical and state-of-the-art optimizers, and concludes them into three main streams: first order optimizers that accelerate convergence speed of stochastic gradient descent or/and adaptively adjust learning rates; second order optimizer that can make use of second-order information of loss landscape which helps escape from local optima.
- 3
- Imaging study of aseptic loosening of the acetabular cup after cementless total hip arthroplasty: a retrospective study3
The combined imaging diagnostic criteria for aseptic loosening of the acetabular cup after total hip arthroplasty demonstrate superior diagnostic efficacy compared to single imaging parameters.
- 3
- 3
- Multifunctional 1050 nm Spectral Domain OCT System at 147 kHz for Posterior Eye Imaging3
It is demonstrated through in-vivo experiments that this SD-OCT system delivers not only superior performance of posterior eye structural imaging but also detailed visualization of microcirculation network in retina.
- 2
- 2
- 2
- Energy-Constrained Deep Neural Network Compression for Depth Estimation2
This work model the training process of a deep neural network for depth estimation under a given energy constraint as a constrained optimization problem and solve it through a proposed projected adaptive cubic quasi-Newton method (termed ProjACQN).
- 2
- 2
- 1
- AdaCN: An Adaptive Cubic Newton Method for Nonconvex Stochastic Optimization1
AdaCN is introduced, a novel adaptive cubic Newton method for nonconvex stochastic optimization that outperforms other stoChastic first order methods and stochastics quasi-Newton method, in terms of both convergence speed and generalization performance.
- 1
- An On-Line Calibration Technique for General Infrared Camera1
This paper proposes an on-line calibration method for general infrared camera where the infrared camera installed on the PAN-Tilt Unit(PTU) is no need calibration board, and uses this method for long distance UAV (Unmanned Aerial Vehicle) detection and localization.
- –
- –
- –
- Depth estimation based on binocular disparity and color-coded aperture fusion–
A novel binocular passive depth sensor with minor hardware modifications on color-coded aperture based on binocular disparity and color- coded aperture depth from defocus fusion algorithm that is outperformance under mismatch and occlusion condition in binocular stereo matching.
- –
- –
- Многофункциональная 1050-нм спектральная ОКТ-система с частотой 147 кГц для визуализации заднего отдела глаза–
A newly developed multifunctional 1050 nm spectral domain optical coherence tomography (SD-OCT) system working at 147 kHz A-scan rate for posterior eye imaging that delivers not only superior performance of posterior eye structural imaging but also detailed visualization of microcirculation network in retina.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.