Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks53 from public data
- Recognition of ischaemia and infection in diabetic foot ulcers: Dataset and techniques233
This work proposes a new dataset and computer vision techniques to identify the presence of infection and ischaemia in DFU, and proposes to use a natural data-augmentation method, which identifies the region of interest on foot images and focuses on finding the salient features existing in this area.
- Content-Aware Unsupervised Deep Homography Estimation204
This work proposes an unsupervised deep homography method with a new architecture design that outperforms the state-of-the-art including deep solutions and feature-based solutions.
- Video Inpainting by Jointly Learning Temporal Structure and Spatial Details188
A novel deep learning architecture is proposed which contains two subnetworks: a temporal structure inference network and a spatial detail recovering network, which jointly trains both sub-networks in an end-to-end manner.
- 110
- UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning96
This work designs a self-guided upsample module to tackle the interpolation blur problem caused by bilinear upsampling between pyramid levels, and proposes a pyramid distillation loss to add supervision for intermediate levels via distilling the finest flow as pseudo labels.
- Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection79
A new framework for unsupervised deep homography estimation is introduced and results show that this approach outperforms the state-of-the-art on the homography benchmark datasets both qualitatively and quantitatively.
- 54
- 49
- UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging With Unpaired Data46
Although the pair data are missing, UPHDR-GAN can properly handle the ghosting artifacts caused by moving objects or misalignments with the help of the modified GAN loss, the improved discriminator network and the useful initialization phase.
- 35
- Changes in Gut Microbiota Structure: A Potential Pathway for Silver Nanoparticles to Affect the Host Metabolism32
The results of the present study demonstrate the importance of considering the roles of GM in the toxicity of NPs to the host in evaluations of the health risks ofNPs.
- 28
- 28
- Semi-Supervised Skin Detection by Network With Mutual Guidance25
Experimental results show the effectiveness of the proposed dual-task neural network for joint detection of skin and body via a semi-supervised learning strategy outperforms the state-of-the-art in skin detection.
- ASFlow: Unsupervised Optical Flow Learning With Adaptive Pyramid Sampling23
This work presents an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network, and proposes a Content-Aware Pooling module, which promotes local feature gathering by avoiding cross region pooling, so that the learned features become more representative.
- 21
- 21
- EpiScan: accurate high-throughput mapping of antibody-specific epitopes using sequence information20
EpiScan can expedite the epitope mapping process for high-throughput antibody sequencing data, supporting vaccine design and drug development, and it is shown that EpiScan, which only uses antibody sequence information, can accurately map epitopes on specific antigen structures.
- Sparse Representation Theory and its Application for Face Recognition13
Experimental results show that face recognition method based on sparse representation is comparable to others, and any test sample can be expressed as a linear span of the all training samples.
- 11
- Automatic segmentation method for bone and blood vessel in murine hindlimb10
The proposed split Bregman method improves the distinguishability between bones and blood vessels, since both the intensity information and the geometrical size are exploited and eliminates the false positive effect on the nonvascular sharp boundaries.
- 9
- 8
- 8
- Potential effects of Ag ion on the host by changing the structure of its gut microbiota5
Overall, the results demonstrate potential effects of Ag on the host, by changing its GM structure, and the need to consider them when evaluating the health risk of Ag.
- 4
- Label-Free Imaging of Humic Substance Bioaccumulation by Pump–Probe Microscopy4
Using a label-free method based on pump-probe microscopy, it is shown HS entered the protozoan Tetrahymena thermophila, zebrafish embryos, and human cells and exerted direct effects on these organisms.
- 4
- Visual Reasoning of Feature Attribution with Deep Recurrent Neural Networks4
This work presents a visual analytics approach to facilitate this task by revealing the RNN attention for all data instances, their temporal positions in the sequences, and the attribution of variables at each value level.
- Marching Windows: Scalable Mesh Generation for Volumetric Data With Multiple Materials3
A novel approach is proposed, called Marching Windows, that uses a moving window and a disk-swap strategy to reduce the run-time memory footprint, devise a new scheme that guarantees to preserve the topological structure of the original dataset, and adopt an error-guided optimization technique to improve both geometric approximation error and mesh quality.
- 3
- A label-free technique to quantify and visualize gold nanoparticle accumulation at the single-cell level3
A novel label-free technique, based on hyperspectral imaging with enhanced darkfield microscopy (HSI-DFM), to visualize and quantify AuNP accumulation at the single-cell level and to monitor the accumulation kinetics of AuNPs in living cells is developed.
- City space type recognition by leveraging deeply-learned topological features3
This work proposes a novel city geometric space classification system, which is inspired by human visual perception toward different geometries within each city, and designed a ranking algorithm to select a few highly discriminative graphlets for city space recognition.
- Semantic Segmentation via Global Convolutional Network and Concatenated Feature Maps3
This paper implements the design concept of DenseNet into a ResNet-based semantic segmentation CNN called Global Convolutional Network (GCN) and builds its own network by switching every identity mapping operation of the decoder network in GCN to a concatenation operation.
- 2
- 2
- 2
- 2
- How to Inherit and Innovate Patterns on the Silk Road in Modern Design1
The aim of research is to discuss how to inherit and innovate graphs of ancient Silk Road in modern design.
- Skin Textural Generation via Blue-noise Gabor Filtering based Generative Adversarial Network1
A novel Blue-Noise Gabor Module to produce a spatial-variant noisy image and a proposed two-branch framework combined facial identity enhancing with textures details generation to jointly produce a high-quality facial image.
- 1
- 1
- –
- –
- –
- –
- Study of Human Behavior Recognition Technology Based on DaVinci Processor–
The paper achieves the method that detects the moving regions using codebook method and train the examples using the K near algorithm and recognize the posture in the video in real time.
- Complementarity Analysis of Affine Region Detectors–
To objectively compare the performance of combination detectors, the matching score is used as an evaluation criterion, which reflects not only the number of correct matches, but also the ratio between correct matches and mismatches.
- –
- –
- –
- –
- –
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 2026-10-15. 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.