Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks307 from public data
- Activating More Pixels in Image Super-Resolution Transformer1,170
A novel Hybrid Attention Transformer (HAT) is proposed, which combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability.
- User's Guide for CFSQP Version 2.0: A C Code for Solving (Large Scale) Constrained Nonlinear (Minimax) Optimization Problems, Generating Iterates Satisfying All Inequality Constraints384
CFSQP is an implementation of two algorithms based on Sequential Quadratic Programming (SQP), modi ed so as to generate feasible iterates and the merit function used in both searches is the maximum of the objective functions if there is no non linear equality constraints, or an exact penalty function if nonlinear equality constraints are present.
- 328
- 309
- Stochastic memristive devices for computing and neuromorphic applications307
This work demonstrates memristor-based stochastic bitstreams in both time and space domains, and shows that an array of binary memristors can act as a multi-level "analog" device for neuromorphic applications.
- 295
- 252
- 225
- 223
- 216
- SmartEdit: Exploring Complex Instruction-Based Image Editing with Multimodal Large Language Models213
A Bidirectional Interaction Module (BIM) is proposed that enables comprehensive bidirectional information interactions between the input image and the MLLM output and demonstrates that a small amount of complex instruction editing data can effectively stimulate SmartEdit’ s editing capabilities for more complex instructions.
- A Review of Compressive Sensing in Information Security Field189
This paper reviews CS in information security field from two aspects: theoretical security and application security, and indicates some other possible application research topics in future.
- HAT: Hybrid Attention Transformer for Image Restoration179
A new Hybrid Attention Transformer (HAT) is proposed that combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages, and achieves state-of-the-art performance both quantitatively and qualitatively.
- 179
- 167
- 153
- 146
- 142
- 142
- 136
- Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities126
A Tag-Assisted Transformer Encoder (TATE) network is proposed to handle the problem of missing uncertain modalities, and a tag encoding module is designed to cover both the single modality and multiple modalities missing cases.
- 123
- A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization119
An adaptive dictionary is designed to bridge the gap between group-based sparse coding (GSC) and rank minimization, and WSNM is found to be the closest one to the real singular values of each patch group and is translated into a non-convex weighted norm minimization problem in GSC.
- From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image Restoration116
Experimental results demonstrate that the proposed RRC method outperforms many state-of-the-art schemes in both the objective and perceptual quality.
- Embedding cryptographic features in compressive sensing114
It is demonstrated that random permutation is an acceptable permutation with overwhelming probability, which can effectively relax the Restricted Isometry Constant for parallel compressive sensing and is utilized to design a secure parallel compression sensing scheme.
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.