Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks328 from public data
- Inpaint Anything: Segment Anything Meets Image Inpainting334
The core idea behind IA is to combine the strengths of different models in order to build a very powerful and user-friendly pipeline for solving inpainting-related problems.
- 213
- Region Normalization for Image Inpainting207
It is shown that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and a spatial region-wise normalization named Region Normalization (RN) is proposed to overcome the limitation.
- Chaos-based image encryption scheme combining DNA coding and entropy192
A secure image encryption scheme based on logistic and spatiotemporal chaotic systems is proposed that can resistant different attacks, such as the brute-force attack, statistical attack and differential attack.
- Neural packet classification140
NeuroCuts is a deep reinforcement learning approach to solve the packet classification problem that uses succinct representations to encode state and action space, and efficiently explore candidate decision trees to optimize for a global objective.
- 140
- ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation110
A GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions, and introduces a new synthetic dataset of complex multi-person combat behaviors.
- SCCGAN: Style and Characters Inpainting Based on CGAN84
The content accuracy and style similarity of the repaired image is used as an evaluation index to evaluate the accuracy of the restored style font.
- Predicting Aesthetic Score Distribution Through Cumulative Jensen-Shannon Divergence74
A novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning methodbased on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human rating data (without normalization).
- Image analysis of tissue sections71
An overview of current methodologies and developments in this field of image transformation, image segmentation and classification is presented and a brief introduction followed by a survey is provided.
- A Unified Pyramid Recurrent Network for Video Frame Interpolation70
UPR-Net is presented, a novel Unified Pyramid Recurrent Network for frame interpolation that leverages estimated bi-directional flow to generate forward-warped representations for frame synthesis and enables iterative refinement for both optical flow and intermediate frame synthesis.
- ILGNet: inception modules with connected local and global features for efficient image aesthetic quality classification using domain adaptation62
A novel deep convolutional neural network named ILGNet is proposed, which combines both the inception modules and a connected layer of both local and global features in order to label an input image as high- or low-aesthetic quality.
- TBFormer: Two-Branch Transformer for Image Forgery Localization59
A Transformer-style network with two feature extraction branches for image forgery localization, named as Two-Branch Transformer (TBFormer), and an Attention-aware Hierarchical-feature Fusion Module (AHFM) is proposed to effectively fuse hierarchical features from two different domains.
- 58
- 57
- 56
- Aesthetic Attributes Assessment of Images55
The evaluation criteria used in image captions is used to prove that the specially designed AMAN model outperforms traditional CNN-LSTM model and modern SCA-CNN model of imageCaptions.
- QPipe53
This paper introduces QPipe, the first quantiles sketching algorithm that can be implemented entirely in the data plane, and gives novel implementations of argmin(), the major building block of SweepKLL which are usually not supported in theData plane of the commodity switch.
- Clump splitting through concavity analysis50
A novel method of decomposing digital binary clumps into constituent convex parts based on the analysis of concavities to determine where splitting should occur is presented.
- FFR_FD: Effective and fast detection of DeepFakes via feature point defects47
For the first time, it is shown that DeepFake faces have fewer feature points than real ones, especially in certain facial regions, and this method is superior to most state of the art DNN-based models.
- 45
- Enhanced Bi-directional Motion Estimation for Video Frame Interpolation41
This work presents a novel compact model to simultaneously estimate the bi-directional motions between input frames within a flexible pyramid recurrent framework, and employs a synthesis network to fuse forward-warped representations and predict the intermediate frame.
- Video encryption based on hyperchaotic system41
Results of experiment show that the proposed video encryption scheme has better security and encryption efficiency than other methods tested, which are compared to each other.
- 3D textured model encryption via 3D Lu chaotic mapping40
This work proposes a 3D Lu chaotic mapping based encryption method that can encrypt and decrypt 3D textured models correctly and typical statistic and brute-force attacks can be resisted by the proposed method.
- Attribute Group Editing for Reliable Few-shot Image Generation37
A new “editing-based” method, i.e., Attribute Group Editing (AGE), for few-shot image generation, capable of not only producing more realistic and diverse images for downstream visual applications with limited data but achieving controllable image editing with interpretable category-irrelevant directions.
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.