Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks169 from public data
- Dense Nested Attention Network for Infrared Small Target Detection1,048
This paper designs a dense nested interactive module (DNIM) to achieve progressive interaction among high-level and low-level features and proposes a cascaded channel and spatial attention module (CSAM) to adaptively enhance multi- level features.
- Unsupervised Degradation Representation Learning for Blind Super-Resolution419
This paper proposes an unsupervised degradation representation learning scheme for blind SR without explicit degradation estimation, and introduces a Degradation-Aware SR (DASR) network with flexible adaption to various degradations based on the learned representations.
- 320
- Learning Parallax Attention for Stereo Image Super-Resolution320
A parallax-attention mechanism with a global receptive field along the epipolar line to handle different stereo images with large disparity variations is introduced and a new and the largest dataset for stereo image SR is proposed.
- MTU-Net: Multilevel TransUNet for Space-Based Infrared Tiny Ship Detection316
A vision Transformer (ViT) convolutional neural network (CNN) hybrid encoder to extract multilevel features and a FocalIoU loss to achieve both target localization and shape description are designed.
- Spatial-Angular Interaction for Light Field Image Super-Resolution208
Experimental results demonstrate the superiority of LF-InterNet over the state-of-the-art methods, i.e., the method can achieve high PSNR and SSIM scores with low computational cost, and recover faithful details in the reconstructed images.
- Recent progress in biomedical applications of persistent luminescence nanoparticles200
PLNPs are demonstrated to be a newly-emerging class of functional materials with unprecedented advantages in biomedicine and can guide cancer therapy with a high signal-to-noise ratio (SNR) and superior sensitivity.
- Light Field Image Super-Resolution With Transformers190
This paper proposes a simple but effective Transformer-based method for LF image SR, designed to incorporate complementary information among different views, and achieves superior SR performance with a small model size and low computational cost.
- A Difunctional Regeneration Scaffold for Knee Repair based on Aptamer‐Directed Cell Recruitment187
An aptamer-bilayer scaffold is designed for autologous mesenchymal stem cell recruitment and osteochondral regeneration that can efficiently recruit MSCs to the defect and induce the directional differentiation of M SCs, thus successfully achieving simultaneous regeneration of cartilage and bone in the knee joint.
- Bioinspired extracellular vesicles embedded with black phosphorus for molecular recognition-guided biomineralization186
The authors report on bioinspired matrix vesicles loaded with black phosphorus nanosheets and cell-specific aptamers for bone regeneration and demonstrate bone defect repair in vivo.
- New insights into the structure–performance relationships of mesoporous materials in analytical science175
The structural properties of mesoporous materials that can be optimized to improve the analytical performance are discussed.
- Deformable 3D Convolution for Video Super-Resolution170
A deformable 3D convolution network (D3Dnet) is proposed to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR, and achieves state-of-the-art SR performance.
- Learning A Single Network for Scale-Arbitrary Super-Resolution162
This paper develops a plug-in module for existing SR networks to perform scale-arbitrary SR, which consists of multiple scale-aware feature adaption blocks and a scale- aware upsampling layer that enables the network to adapt to arbitrary scale factors.
- Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision159
This paper proposes a label evolution framework named label evolution with single point supervision (LESPS) to progressively expand the point label by leveraging the intermediate predictions of CNNs, and shows that CNNs equipped with LESPS can well recover the target masks from corresponding point labels.
- Parallax Attention for Unsupervised Stereo Correspondence Learning159
A generic parallax-attention mechanism (PAM) to capture stereo correspondence regardless of disparity variations is proposed and Experimental results show that the PAM is generic and can effectively learn stereo correspondence under large disparity variations in an unsupervised manner.
- Photon-Responsive Antibacterial Nanoplatform for Synergistic Photothermal-/Pharmaco-Therapy of Skin Infection157
A photon-controlled antibacterial platform designed by encapsulating black phosphorus quantum dots and pharmaceuticals inside a thermal-sensitive liposome can open new possibilities for avoiding bacterial resistance and efficiently killing antibiotic-resistant bacteria, making it valuable in fields ranging from antiinfective therapy to precision medicine.
- Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolution155
This letter proposes a light field refocusing method that can selectively refocus images with focused region being superresolved and bokeh being esthetically rendered and enables postadjustment of depth of field.
- 153
- Direction-Coded Temporal U-Shape Module for Multiframe Infrared Small Target Detection145
A simple yet effective direction-coded temporal U-shape module (DTUM) for MIRST detection and a motion-to-data mapping to distinguish the motion of targets and clutters by indexing different directions, which achieves the state-of-the-art performance in detecting infrared small and dim targets and suppressing false alarms.
- Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark145
A large-scale satellite video dataset with rich annotations for the task of moving object detection and tracking is built and a motion modeling baseline is introduced to improve the detection rate and reduce false alarms.
- A Stereo Attention Module for Stereo Image Super-Resolution143
Using SAM, the generic stereo attention module (SAM) is proposed to extend arbitrary SISR networks to stereo images and can exploit cross-view information while maintaining the superiority of intra-View information exploitation, resulting in notable performance gain to SisR networks.
- Recent progress in background-free latent fingerprint imaging128
This review is organized around background-free LFP imaging based on the difference in optical properties between contrast agents and background compounds: (i) different excitation wavelengths, (ii) different emission wavelengths, (-) different luminescence lifetime values, (iv) different plasmonic properties, (v) different photothermal properties, and (vi) different electrochemiluminescence properties.
- Nonconvex Tensor Low-Rank Approximation for Infrared Small Target Detection120
This paper proposes a non-convex tensor low-rank approximation (NTLA) method for infrared small target detection, which has strong robustness and low false-alarm rate and proposes asymmetric spatial-temporal total variation (ASTTV) regularization to achieve more accurate background estimation in complex scenes.
- Occlusion-Aware Cost Constructor for Light Field Depth Estimation114
A simple and fast cost constructor to construct matching cost for LF depth estimation, composed by a series of convolutions with specifically designed dilation rates, which is occlusion-aware and can handle occlusions by dynamically modulating pixels from different views.
- Time-Gated Imaging of Latent Fingerprints and Specific Visualization of Protein Secretions via Molecular Recognition114
Results proved the potent ability of Zn2GeO4:Ga,Mn in eliminating background fluorescence to afford highly sensitive LFP imaging and provides great versatility in LFP Imaging and good potential in uncovering the chemical information within LFP, making it valuable in forensic investigations and medical diagnostics.
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.