Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks45 from public data
- Deep High-Resolution Representation Learning for Human Pose Estimation5,649
This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.
- Deep High-Resolution Representation Learning for Visual Recognition5,145
The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.
- 614
- Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression401
It is empirically show that the proposed direct regression method outperforms keypoint detection and grouping methods and achieves superior bottom-up pose estimation results on two benchmark datasets, COCO and CrowdPose.
- Direct data domain STAP using sparse representation of clutter spectrum166
D3SR maintains the full system DOF so that it can achieve better performance of output signal-clutter-ratio (SCR) and minimum detectable velocity (MDV) than current D3 methods, e.g., direct data domain least squares (D3LS).
- 96
- 92
- DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset72
This paper presents DuSQL, a larges-scale and pragmatic Chinese dataset for the cross-domain text-to-SQL task, containing 200 databases, 813 tables, and 23,797 question/SQL pairs, and adopts an effective data construction framework via human-computer collaboration.
- Human Pose Estimation Using Global and Local Normalization71
A two-stage normalization scheme, human body normalization and limb normalization, is presented to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation.
- Dunhuang murals image restoration method based on generative adversarial network62
A generative adversarial network model combining a parallel dual convolutional feature extraction depth generator and a ternary heterogeneous joint discriminator is proposed, which has an overall improvement in the evaluation metrics of PSNR and SSIM compared with the comparative methods.
- Detecting decayed peach using a rotating hyperspectral imaging testbed48
The results demonstrated that the hyperspectral imaging method offers the potential to be used to automatically detect fungal infection in peaches.
- 40
- GAN-based heterogeneous network for ancient mural restoration36
An innovative mural restoration approach using a generative adversarial network (GAN) within a UNet architecture that integrates Transformer and convolutional neural network components, effectively capturing and reconstructing complex mural features.
- Efficient kNN Algorithm Based on Graph Sparse Reconstruction34
The experimental results show that the proposed GS-kNN algorithm outperforms the previous kNN algorithms in terms of classification accuracy, correlation coefficient and root mean square error (RMSE).
- Registration-based compensation using sparse representation in conformal-array STAP31
This paper proposes a new compensation method, namely RBC with sparse representation (SR-RBC), which provides more accurate clutter spectral estimation, and the transformed training data are more stationary so that better signal-clutter-ratio (SCR) improvement is achieved.
- Feature selection by combining subspace learning with sparse representation28
A novel feature selection algorithm is designed for high-dimensional data classification to select the most representative features and noise-resistant features to enhance the performance of classification.
- Adaptive Sparse Representation for Source Localization with Gain/Phase Errors27
An adaptive SR algorithm is proposed to improve the robustness with respect to the gain/phase error, where the overcomplete basis is dynamically adjusted using multiple snapshots and the sparse solution is adaptively acquired to match with the actual scenario.
- High-Order Tensor Pooling with Attention for Action Recognition24
The HDP and the EPN play the same role, i.e., to boost or dampen the magnitude of the eigenspectrum thus preventing the burstiness, and it is proved that for a tensor of order r built from d dimensional feature descriptors, such a detector gives the likelihood if at least one higher-order occurrence is 'projected' into one of binom(d,r) subspaces represented by the tensor.
- Recognition of Mould Colony on Unhulled Paddy Based on Computer Vision using Conventional Machine-learning and Deep Learning Techniques24
A pitch segmentation recognition method combined with different classification models was developed to recognize the mould colony areas in the image and an efficient uniform CNN pitch classification model was built.
- 23
- Synergy between Semantic Segmentation and Image Denoising via Alternate Boosting20
It is observed that not onlyDenoising helps combat the drop of segmentation accuracy due to the noisy input, but also pixel-wise semantic information boosts the capability of denoising.
- 17
- 17
- Sequenced wave signal extraction and classification algorithm for duck egg crack on-line detection15
The analysis results showed that, the sequenced wave signals extracted from egg translucent images are caused by three factors: (i) egg cracks; (ii) air cell membrane of eggs; and (iii) shell texture.
- 14
- Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding13
An interpretable deep structure namely Frank- Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving the non-sparse coding problem, is proposed and the hyper-parameter can be made learnable instead of pre-chosen in F-WNet.
- L p -Norm Constrained Coding With Frank-Wolfe Network.12
An interpretable deep structure namely Frank- Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving the non-sparse coding problem, is proposed and the hyper-parameter can be made learnable instead of pre-chosen in F-WNet.
- Learning Deep Image Priors for Blind Image Denoising10
The results demonstrate the effectiveness of the approach for robust image denoising on both synthetic and real-world noisy images, and show that the feature-level prior is capable of alleviating the discrepancy between different level noise.
- 7
- Recognition of a Cracked Hen Egg Image Using a Sequenced Wave Signal Extraction and Identification Algorithm6
In order to develop a new recognition method for cracked hen egg with high accuracy and adoption, images with different crack width of the hen eggs were captured and a sequenced wave signal extraction and identification algorithm was developed.
- 4
- 4
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- –
- –
- –
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 2026-10-16. 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.