Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks40 from public data
- Off-line signature verification by the tracking of feature and stroke positions190
The proposed system compares favorably with other methods and outperforms the volunteers when it comes to verifying the authenticity of a signature.
- Offline signature verification with generated training samples61
Results showed that the additional samples generated by the proposed elastic matching method could reduce the error rate from 15.6% to 11.4% and it outperformed another existing method which estimates the class covariance matrix through optimisation techniques.
- 32
- Improved Class Statistics Estimation for Sparse Data Problems in Offline Signature Verification28
Two methods to improve the statistics estimation of offline signature verification are proposed, one employing an elastic distortion model, and the other adopting regularization techniques to overcome the problem of inverting an ill-conditioned sample covariance matrix due to insufficient training samples.
- Prompt Engineering Through the Lens of Optimal Control24
This framework provides a unified mathematical structure that not only systematizes the existing PE methods but also sets the stage for rigorous analytical improvements and extends this framework to include PE via ensemble methods and multi-agent collaboration, thereby enlarging the scope of applicability.
- Printed Chinese Character Similarity Measurement Using Ring Projection and Distance Transform24
A new Chinese character similarity measurement method based on the ring projection algorithm and distance transform to solve the nonlinear distortion problem and a number of Chinese characters are selected to evaluate the capability.
- Reduction of Feature Statistics Estimation Error for Small Training Sample Size in Off-Line Signature Verification14
Two methods to tackle the sparse data problem in off-line signature verification are proposed to artificially generate additional training samples from the existing training set by an elastic matching technique and stabilized estimation of feature statistics.
- Query-Guided Prototype Learning with Decoder Alignment and Dynamic Fusion in Few-Shot Segmentation12
A query-guided prototype learning architecture to address the problem of inaccurate predictions when directly compared with features extracted from the query set, and proposes a cross-alignment loss for training the segmentation decoder.
- Embedding torus in hexagonal honeycomb torus12
The study proves that a (3n, 2n) torus can be embedded into an nth-order HHT with dilation 3, congestion 4, expansion 1 and load factor 1, and can be executed on an nnth- order HHT efficiently.
- 9
- 7
- 7
- 5
- 4
- Distributed Autonomous Agents for Chinese Document Image Segmentation4
A novel computational paradigm for extracting text/graphic blocks from Chinese document images, which is based on a notion of distributed autonomous agents that are adaptive to the locality of given images and hence efficient in locating the homogeneous image blocks.
- 3
- 3
- CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis2
This work introduces CXR-LanIC (Language-Grounded Interpretable Classifier for Chest X-rays), a novel framework that addresses this interpretability challenge through task-aligned pattern discovery, and extracts interpretable features from a classifier trained on specific diagnostic objectives rather than general-purpose embeddings.
- 2
- 2
- 2
- 2
- 2
- 2
- 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 2026-10-11. 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. You will be asked to sign in.