Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks98 from public data
- Res2Net: A New Multi-Scale Backbone Architecture3,382
This paper proposes a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block that represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.
- Deep Hough Transform for Semantic Line Detection248
This paper incorporates the classical Hough transform technique into deeply learned representations and proposes a one-shot end-to-end learning framework for line detection by parameterizing lines with slopes and biases, which transforms the problem of detecting semantic lines in the spatial domain into spotting individual points in the parametric domain.
- Video Polyp Segmentation: A Deep Learning Perspective193
This work introduces a high-quality frame-by-frame annotated VPS dataset, named SUN-SEG, which contains 158 690 colonoscopy video frames from the well-known SUN-database and designs a simple but efficient baseline, named PNS+, which achieves the best performance and real-time inference speed.
- Deep Regression Forests for Age Estimation180
The proposed Deep Regression Forests (DRFs), an end-to-end model for age estimation, connect the split nodes to a fully connected layer of a convolutional neural network (CNN) and deal with inhomogeneous data by jointly learning input-dependant data partitions at the split node and data abstractions at the leaf nodes.
- 122
- 119
- DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images109
This paper presents a novel fully convolutional network with multiple scale-associated side outputs to address object skeleton extraction from natural images, and achieves promising results on two skeleton extraction datasets, and significantly outperforms other competitors.
- 95
- Optimizing the F-Measure for Threshold-Free Salient Object Detection86
The relaxed F-measure is proposed which is differentiable w.r.t the posterior and can be easily appended to the back of CNNs as the loss function, named FLoss, which can continuously force the network to produce polarized activations.
- 75
- 71
- Med-cDiff: Conditional Medical Image Generation with Diffusion Models64
This paper introduces the use of conditional Denoising Diffusion Probabilistic Models (cDDPMs) for medical image generation, which achieve state-of-the-art performance on severalmedical image generation tasks.
- Translate-to-Recognize Networks for RGB-D Scene Recognition58
A unified framework to integrate the tasks of cross-modal translation and modality-specific recognition, termed as Translate-to-Recognize Network TRecgNet, which achieves superior performance to the existing state-of-the-art methods, especially for recognition solely based on a single modality.
- Hi-Fi: Hierarchical Feature Integration for Skeleton Detection55
A new convolutional neural network architecture is presented by introducing a novel hierarchical feature integration mechanism, named Hi-Fi, to address the object skeleton detection problem and significantly outperforms the state-of-the-art methods in terms of effectively fusing features from very different scales.
- ContrastMask: Contrastive Learning to Segment Every Thing51
This paper proposes a new method, named ContrastMask, which learns a mask segmentation model on both base and novel categories under a unified pixel-level contrastive learning framework, and demonstrates the superiority of this method, which outperforms previous state-of-the-arts methods.
- 48
- MRI Super-Resolution With Partial Diffusion Models40
Experiments demonstrate that partial diffusion models achieve competetive super-resolution quality with significantly fewer denoising steps than original diffusion models and can be incorporated with recent accelerated diffusion models to further enhance the efficiency.
- Evaluating association rules and decision trees to predict multiple target attributes39
This work conducts an extensive experimental evaluation on a real medical data set to mine rules predicting disease on multiple heart arteries, and shows association rules, compared to decision trees, tend to have higher confidence, they involve larger subsets of the data set, they are better for multiple target attributes, and they work better with user-defined binning.
- A Lightweight U-Net Architecture Multi-Scale Convolutional Network for Pediatric Hand Bone Segmentation in X-Ray Image37
This study proposes a lightweight U-Net architecture multi-scale convolutional network for pediatric hand bone segmentation in the X-ray image and results indicate promising performance in hand bones segmenting, especially for small bones of the hand.
- A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification31
A robust descriptor based on the principal curvatures (PCs) and rotation invariant version of CLBP_Sign operator in completed LBP (CLBP) is introduced, namely PC-LBP, which achieves comparable performance or outperforms a large number of state-of-the-art methods in texture classification with multiresolution.
- 30
- Refining Uncertain Features With Self-Distillation for Face Recognition and Person Re-Identification24
- 23
- 22
- 21
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 2026-10-13. 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.