Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks482 from public data
- 768
- Hyperspectral Image Classification With Attention-Aided CNNs340
An attention-aided CNN model based on the traditional CNN model that incorporates attention modules to aid networks that focus on more discriminative channels or positions for spectral and spatial classifications of hyperspectral images is proposed.
- Multiscale Point Cloud Geometry Compression268
This paper proposes a multiscale end-to-end learning framework that hierarchically reconstructs the 3D Point Cloud Geometry (PCG) via progressive re-sampling on top of a sparse convolution based autoencoder for point cloud compression and reconstruction.
- 238
- Sparse Tensor-Based Multiscale Representation for Point Cloud Geometry Compression221
A unified Point Cloud Geometry compression method through the processing of multiscale sparse tensor-based voxelized PCG that not only shows state-of-the-art performance in both lossless and lossy compression modes across a variety of datasets, but also has low complexity which is attractive to practical applications.
- 138
- CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting133
An efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size and develops a rate-constrained optimization scheme to eliminate redundancies.
- An Efficient Four-Parameter Affine Motion Model for Video Coding114
A simplified affine motion model-based coding framework to overcome the limitation of a translational motion model and maintain low-computational complexity is studied.
- 105
- Pseudo-Sequence-Based 2-D Hierarchical Coding Structure for Light-Field Image Compression101
The experimental results demonstrate that the proposed novel pseudo-sequence based 2-D hierarchical structure can achieve maximum 14.2% bit-rate savings compared with the state-of-the-art light-field image compression method.
- 94
- 90
- 86
- 85
- 80
- 76
- Asymmetric color cryptosystem using chaotic Ushiki map and equal modulus decomposition in fractional Fourier transform domains74
The Ushiki chaotic system is performed to generate the random phase mask in FrFT and a random sequence for scrambling the private key in a single optical channel system to enhance the security of the proposed cryptosystem.
- Inter-Frame Compression for Dynamic Point Cloud Geometry Coding70
A deep learning-based inter-frame encoding scheme for dynamic point cloud geometry compression that predicts the latent representation of the current frame using the previous frame by employing a novel feature space inter-prediction network.
- 70
- 66
- Early diagnosis of Parkinson's disease using Continuous Convolution Network: Handwriting recognition based on off-line hand drawing without template62
This paper studies various features of spiral hand drawing of Parkinson's disease and develops an auxiliary diagnosis scheme based on hand drawing, and Continuous Convolution Network (CC-Net) is proposed to reduce the pooling layer.
- Attribute compression of 3D point clouds using Laplacian sparsity optimized graph transform60
A new binary tree based point cloud partition is introduced and the graph signal processing tools, especially the graph transform with optimized Laplacian sparsity, are explored to achieve better energy compaction and compression efficiency.
- 58
- PoseMapGait: A model-based gait recognition method with pose estimation maps and graph convolutional networks58
This paper exploits the byproduct of pose estimation maps, which denotes the invariant features of whole body structure and body pose joints for gait recognition, respectively, and achieves the new state-of-the-art performance compared with recent advanced model-based methods.
- Video-Based Point Cloud Compression Artifact Removal57
This work developed a novel out-of-the-loop point cloud geometry artifact removal solution that can significantly improve reconstruction quality without additional bandwidth cost and jointly recovers both the quantization direction and the quantification noise level by exploiting projection and quantization prior.
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.